In open-ended environments, autonomous learning agents must set their own goals and build their own curriculum through an intrinsically motivated exploration. They may consider a large diversity of goals, aiming to discover what is controllable in their environments, and what is not. Because some goals might prove easy and some impossible, agents must actively select which goal to practice at any moment, to maximize their overall mastery on the set of learnable goals. This paper proposes CURIOUS, an algorithm that leverages 1) a modular Universal Value Function Approximator with hindsight learning to achieve a diversity of goals of different kinds within a unique policy and 2) an automated curriculum learning mechanism that biases the attention of the agent towards goals maximizing the absolute learning progress. Agents focus sequentially on goals of increasing complexity, and focus back on goals that are being forgotten. Experiments conducted in a new modular-goal robotic environment show the resulting developmental self-organization of a learning curriculum, and demonstrate properties of robustness to distracting goals, forgetting and changes in body properties.
http://arxiv.org/abs/1810.06284
Temporal point process is an expressive tool for modeling event sequences over time. In this paper, we take a reinforcement learning view whereby the observed sequences are assumed to be generated from a mixture of latent policies. The purpose is to cluster the sequences with different temporal patterns into the underlying policies while learning each of the policy model. The flexibility of our model lies in: i) all the components are networks including the policy network for modeling the intensity function of temporal point process; ii) to handle varying-length event sequences, we resort to inverse reinforcement learning by decomposing the observed sequence into states (RNN hidden embedding of history) and actions (time interval to next event) in order to learn the reward function, thus achieving better performance or increasing efficiency compared to existing methods using rewards over the entire sequence such as log-likelihood or Wasserstein distance. We adopt an expectation-maximization framework with the E-step estimating the cluster labels for each sequence, and the M-step aiming to learn the respective policy. Extensive experiments show the efficacy of our method against state-of-the-arts.
http://arxiv.org/abs/1905.12345
We propose the introduction of nonlinear operation into the feature generation process in convolutional neural networks. This nonlinearity can be implemented in various ways. First we discuss the use of nonlinearities in the process of data augmentation to increase the robustness of the neural networks recognition capacity. To this end, we randomly disturb the input data set by applying exponents within a certain numerical range to individual data points of the input space. Second we propose nonlinear convolutional neural networks where we apply the exponential operation to each element of the receptive field. To this end, we define an additional weight matrix of the same dimension as the standard kernel weight matrix. The weights of this matrix then constitute the exponents of the corresponding components of the receptive field. In the basic setting, we keep the weight parameters fixed during training by defining suitable parameters. Alternatively, we make the exponential weight parameters end-to-end trainable using a suitable parameterization. The network architecture is applied to time series analysis data set showing a considerable increase in the classification performance compared to baseline networks.
http://arxiv.org/abs/1905.12337
The recent introduction of entity-centric implicit network represen-tations of unstructured text offers novel ways for exploring entityrelations in document collections and streams efficiently and inter-actively. Here, we present TopExNet as a tool for exploring entity-centric network topics in streams of news articles. The application isavailable as a web service at https://topexnet.ifi.uni-heidelberg.de/ .
http://arxiv.org/abs/1905.12335
Sequence-processing neural networks led to remarkable progress on many NLP tasks. As a consequence, there has been increasing interest in understanding to what extent they process language as humans do. We aim here to uncover which biases such models display with respect to natural" word-order constraints. We train models to communicate about paths in a simple gridworld, using miniature languages that reflect or violate various natural language trends, such as the tendency to avoid redundancy or to minimize long-distance dependencies. We study how the controlled characteristics of our miniature languages affect individual learning and their stability across multiple network generations. The results draw a mixed picture. On the one hand, neural networks show a strong tendency to avoid long-distance dependencies. On the other hand, there is no clear preference for the efficient, non-redundant encoding of information that is widely attested in natural language. We thus suggest inoculating a notion ofeffort’’ into neural networks, as a possible way to make their linguistic behavior more human-like.
http://arxiv.org/abs/1905.12330
In this paper we present a new definition of the distortion matrix for a score following framework based on DTW. The proposal consists of arranging the score information in a sequence of note combinations and learning a spectral pattern for each combination using instrument models. Then, the distortion matrix is computed using these spectral patterns and a novel decomposition of the input signal.
http://arxiv.org/abs/1905.12324
Deep learning has become an area of interest in most scientific areas, including physical sciences. Modern networks apply real-valued transformations on the data. Particularly, convolutions in convolutional neural networks discard phase information entirely. Many deterministic signals, such as seismic data or electrical signals, contain significant information in the phase of the signal. We explore complex-valued deep convolutional networks to leverage non-linear feature maps. Seismic data commonly has a lowcut filter applied, to attenuate noise from ocean waves and similar long wavelength contributions. Discarding the phase information leads to low-frequency aliasing analogous to the Nyquist-Shannon theorem for high frequencies. In non-stationary data, the phase content can stabilize training and improve the generalizability of neural networks. While it has been shown that phase content can be restored in deep neural networks, we show how including phase information in feature maps improves both training and inference from deterministic physical data. Furthermore, we show that the reduction of parameters in a complex network results in training on a smaller dataset without overfitting, in comparison to a real-valued network with the same performance.
http://arxiv.org/abs/1905.12321
Performing supervised learning from the data synthesized by using Generative Adversarial Networks (GANs), dubbed GAN-synthetic data, has two important applications. First, GANs may generate more labeled training data, which may help improve classification accuracy. Second, in scenarios where real data cannot be released outside certain premises for privacy and/or security reasons, using GAN- synthetic data to conduct training is a plausible alternative. This paper proposes a generalization bound to guarantee the generalization capability of a classifier learning from GAN-synthetic data. This generalization bound helps developers gauge the generalization gap between learning from synthetic data and testing on real data, and can therefore provide the clues to improve the generalization capability.
https://arxiv.org/abs/1905.12313
Imitation learning targets deriving a mapping from states to actions, a.k.a. policy, from expert demonstrations. Existing methods for imitation learning typically require any actions in the demonstrations to be fully available, which is hard to ensure in real applications. Though algorithms for learning with unobservable actions have been proposed, they focus solely on state information and overlook the fact that the action sequence could still be partially available and provide useful information for policy deriving. In this paper, we propose a novel algorithm called Action-Guided Adversarial Imitation Learning (AGAIL) that learns a policy from demonstrations with incomplete action sequences, i.e., incomplete demonstrations. The core idea of AGAIL is to separate demonstrations into state and action trajectories, and train a policy with state trajectories while using actions as auxiliary information to guide the training whenever applicable. Built upon the Generative Adversarial Imitation Learning, AGAIL has three components: a generator, a discriminator, and a guide. The generator learns a policy with rewards provided by the discriminator, which tries to distinguish state distributions between demonstrations and samples generated by the policy. The guide provides additional rewards to the generator when demonstrated actions for specific states are available. We compare AGAIL to other methods on benchmark tasks and show that AGAIL consistently delivers comparable performance to the state-of-the-art methods even when the action sequence in demonstrations is only partially available.
http://arxiv.org/abs/1905.12310
Typical methods for unsupervised text style transfer often rely on two key ingredients: 1) seeking for the disentanglement of the content and the attributes, and 2) troublesome adversarial learning. In this paper, we show that neither of these components is indispensable. We propose a new framework without them and instead consists of three key components: a variational auto-encoder (VAE), some attribute predictors (one for each attribute), and a content predictor. The VAE and the two types of predictors enable us to perform gradient-based optimization in the continuous space, which is mapped from sentences in a discrete space, to find the representation of a target sentence with the desired attributes and preserved content. Moreover, the proposed method can, for the first time, simultaneously manipulate multiple fine-grained attributes, such as sentence length and the presence of specific words, in synergy when performing text style transfer tasks. Extensive experimental studies on three popular text style transfer tasks show that the proposed method significantly outperforms five state-of-the-art methods.
http://arxiv.org/abs/1905.12304
Policy optimization on high-dimensional continuous control tasks exhibits its difficulty caused by the large variance of the policy gradient estimators. We present the action subspace dependent gradient (ASDG) estimator which incorporates the Rao-Blackwell theorem (RB) and Control Variates (CV) into a unified framework to reduce the variance. To invoke RB, our proposed algorithm (POSA) learns the underlying factorization structure among the action space based on the second-order advantage information. POSA captures the quadratic information explicitly and efficiently by utilizing the wide & deep architecture. Empirical studies show that our proposed approach demonstrates the performance improvements on high-dimensional synthetic settings and OpenAI Gym’s MuJoCo continuous control tasks.
http://arxiv.org/abs/1805.03586
Achieving advancements in automatic recognition of emotions that music can induce require considering multiplicity and simultaneity of emotions. Comparison of different machine learning algorithms performing multilabel and multiclass classification is the core of our work. The study analyzes the implementation of the Geneva Emotional Music Scale 9 in the Emotify music dataset and the data distribution. The research goal is the identification of best methods towards the definition of the audio component of a new a new multimodal dataset for music emotion recognition.
http://arxiv.org/abs/1905.12629
We present a deep generative model of bilingual sentence pairs for machine translation. The model generates source and target sentences jointly from a shared latent representation and is parameterised by neural networks. We perform efficient training using amortised variational inference and reparameterised gradients. Additionally, we discuss the statistical implications of joint modelling and propose an efficient approximation to maximum a posteriori decoding for fast test-time predictions. We demonstrate the effectiveness of our model in three machine translation scenarios: in-domain training, mixed-domain training, and learning from a mix of gold-standard and synthetic data. Our experiments show consistently that our joint formulation outperforms conditional modelling (i.e. standard neural machine translation) in all such scenarios.
http://arxiv.org/abs/1807.10564
Recovering an image from a noisy observation is a key problem in signal processing. Recently, it has been shown that data-driven approaches employing convolutional neural networks can outperform classical model-based techniques, because they can capture more powerful and discriminative features. However, since these methods are based on convolutional operations, they are only capable of exploiting local similarities without taking into account non-local self-similarities. In this paper we propose a convolutional neural network that employs graph-convolutional layers in order to exploit both local and non-local similarities. The graph-convolutional layers dynamically construct neighborhoods in the feature space to detect latent correlations in the feature maps produced by the hidden layers. The experimental results show that the proposed architecture outperforms classical convolutional neural networks for the denoising task.
http://arxiv.org/abs/1905.12281
Word representation is a key component in neural-network-based sequence labeling systems. However, representations of unseen or rare words trained on the end task are usually poor for appreciable performance. This is commonly referred to as the out-of-vocabulary (OOV) problem. In this work, we address the OOV problem in sequence labeling using only training data of the task. To this end, we propose a novel method to predict representations for OOV words from their surface-forms (e.g., character sequence) and contexts. The method is specifically designed to avoid the error propagation problem suffered by existing approaches in the same paradigm. To evaluate its effectiveness, we performed extensive empirical studies on four part-of-speech tagging (POS) tasks and four named entity recognition (NER) tasks. Experimental results show that the proposed method can achieve better or competitive performance on the OOV problem compared with existing state-of-the-art methods.
http://arxiv.org/abs/1905.12277
Human Activity Recognition (HAR) using deep neural network has become a hot topic in human-computer interaction. Machine can effectively identify human naturalistic activities by learning from a large collection of sensor data. Activity recognition is not only an interesting research problem, but also has many real-world practical applications. Based on the success of residual networks in achieving a high level of aesthetic representation of the automatic learning, we propose a novel \textbf{A}symmetric \textbf{R}esidual \textbf{N}etwork, named ARN. ARN is implemented using two identical path frameworks consisting of (1) a short time window, which is used to capture spatial features, and (2) a long time window, which is used to capture fine temporal features. The long time window path can be made very lightweight by reducing its channel capacity, yet still being able to learn useful temporal representations for activity recognition. In this paper, we mainly focus on proposing a new model to improve the accuracy of HAR. In order to demonstrate the effectiveness of ARN model, we carried out extensive experiments on benchmark datasets (i.e., OPPORTUNITY, UniMiB-SHAR) and compared with some conventional and state-of-the-art learning-based methods. Then, we discuss the influence of networks parameters on performance to provide insights about its optimization. Results from our experiments show that ARN is effective in recognizing human activities via wearable datasets.
http://arxiv.org/abs/1903.05359
Diagnosis and treatment guidance are aided by detecting relevant biomarkers in medical images. Although supervised deep learning can perform accurate segmentation of pathological areas, it is limited by requiring a-priori definitions of these regions, large-scale annotations, and a representative patient cohort in the training set. In contrast, anomaly detection is not limited to specific definitions of pathologies and allows for training on healthy samples without annotation. Anomalous regions can then serve as candidates for biomarker discovery. Knowledge about normal anatomical structure brings implicit information for detecting anomalies. We propose to take advantage of this property using bayesian deep learning, based on the assumption that epistemic uncertainties will correlate with anatomical deviations from a normal training set. A Bayesian U-Net is trained on a well-defined healthy environment using weak labels of healthy anatomy produced by existing methods. At test time, we capture epistemic uncertainty estimates of our model using Monte Carlo dropout. A novel post-processing technique is then applied to exploit these estimates and transfer their layered appearance to smooth blob-shaped segmentations of the anomalies. We experimentally validated this approach in retinal optical coherence tomography (OCT) images, using weak labels of retinal layers. Our method achieved a Dice index of 0.789 in an independent anomaly test set of age-related macular degeneration (AMD) cases. The resulting segmentations allowed very high accuracy for separating healthy and diseased cases with late wet AMD, dry geographic atrophy (GA), diabetic macular edema (DME) and retinal vein occlusion (RVO). Finally, we qualitatively observed that our approach can also detect other deviations in normal scans such as cut edge artifacts.
http://arxiv.org/abs/1905.12806
This paper presents a novel multi-attention driven system that jointly exploits Convolutional Neural Network (CNN) and Recurrent Neural Network (RNN) in the context of multi-label remote sensing (RS) image classification. The proposed system consists of four main modules. The first module aims to extract preliminary local descriptors of RS image bands that can be associated to different spatial resolutions. To this end, we introduce a K-Branch CNN, in which each branch extracts descriptors of image bands that have the same spatial resolution. The second module aims to model spatial relationship among local descriptors. This is achieved by a bidirectional RNN architecture, in which Long Short-Term Memory nodes enrich local descriptors by considering spatial relationships of local areas (image patches). The third module aims to define multiple attention scores for local descriptors. This is achieved by a novel patch-based multi-attention mechanism that takes into account the joint occurrence of multiple land-cover classes and provides the attention-based local descriptors. The last module exploits these descriptors for multi-label RS image classification. Experimental results obtained on the BigEarthNet that is a large-scale Sentinel-2 benchmark archive show the effectiveness of the proposed method compared to a state of the art method.
http://arxiv.org/abs/1902.11274
The effectiveness of Symmetric Positive Definite (SPD) manifold features has been proven in various computer vision tasks. However, due to the non-Euclidean geometry of these features, existing Euclidean machineries cannot be directly used. In this paper, we tackle the classification tasks with limited training data on SPD manifolds. Our proposed framework, named Manifold Convex Class Model, represents each class on SPD manifolds using a convex model, and classification can be performed by computing distances to the convex models. We provide three methods based on different metrics to address the optimization problem of the smallest distance of a point to the convex model on SPD manifold. The efficacy of our proposed framework is demonstrated both on synthetic data and several computer vision tasks including object recognition, texture classification, person re-identification and traffic scene classification.
http://arxiv.org/abs/1806.05343
Mining temporal assertions from time-series data using information theory to filter real properties from incidental ones is a practically significant challenge. The problem is complex for continuous or hybrid systems because the degrees of influence on a consequent from a timed-sequence of predicates (called its prefix sequence), varies continuously over dense time intervals. We propose a parameterized method that uses interval arithmetic for flexibly learning prefix sequences having influence on a defined consequent over various time scales and predicates over system variables.
http://arxiv.org/abs/1905.12262
Generative adversarial networks (GANs) learn to mimic training data that represents the underlying true data distribution. However, GANs suffer when the training data lacks quantity or diversity and therefore cannot represent the underlying distribution well. To improve the performance of GANs trained on under-represented training data distributions, this paper proposes KG-GAN to fuse domain knowledge with the GAN framework. KG-GAN trains two generators; one learns from data while the other learns from knowledge. To achieve KG-GAN, domain knowledge is formulated as a constraint function to guide the learning of the second generator. We validate our framework on two tasks: fine-grained image generation and hair recoloring. Experimental results demonstrate the effectiveness of KG-GAN.
http://arxiv.org/abs/1905.12261
There has been significant interest recently in learning multilingual word embeddings – in which semantically similar words across languages have similar embeddings. State-of-the-art approaches have relied on expensive labeled data, which is unavailable for low-resource languages, or have involved post-hoc unification of monolingual embeddings. In the present paper, we investigate the efficacy of multilingual embeddings learned from weakly-supervised image-text data. In particular, we propose methods for learning multilingual embeddings using image-text data, by enforcing similarity between the representations of the image and that of the text. Our experiments reveal that even without using any expensive labeled data, a bag-of-words-based embedding model trained on image-text data achieves performance comparable to the state-of-the-art on crosslingual semantic similarity tasks.
http://arxiv.org/abs/1905.12260
Advances in learning and representations have reinvigorated work that connects language to other modalities. A particularly exciting direction is Vision-and-Language Navigation (VLN), in which agents interpret natural language instructions and visual scenes to move through environments and reach goals. Despite recent progress, current research leaves unclear how much of a role language understanding plays in this task, especially because dominant evaluation metrics have focused on goal completion rather than the sequence of actions corresponding to the instructions. Here, we highlight shortcomings of current metrics for the Room-to-Room dataset \cite{Anderson:2018:VLN} and propose a new metric, Coverage weighted by Length Score. We also show that the existing paths in the dataset are not ideal for evaluating instruction following because they are direct-to-goal shortest paths. We join existing short paths to create more challenging extended paths, and show that agents that receive rewards for instruction fidelity outperform agents that focus on goal completion.
http://arxiv.org/abs/1905.12255
We consider differentially private algorithms for reinforcement learning in continuous state spaces, such that neighboring reward functions are indistinguishable. Existing studies that guarantee differential privacy are not extendable to infinite state spaces, since the noise level to ensure privacy will scale accordingly to infinity. Our aim is to protect the privacy for the value function approximator, without regard to the number of states queried to the function. We add functional noise to the value function iteratively in the training. We show rigorous privacy guarantees by a series of analyses on the kernel of the noise space, the probabilistic bound of such noise samples, and the composition of the noise. We gain insight into the utility analysis by proving the algorithm’s approximate optimality, under the discrete state space setting. Experiments corroborate our theoretical findings and show improvement over existing methods.
http://arxiv.org/abs/1901.10634
Spectral imaging has recently gained traction for face recognition in biometric systems. We investigate the merits of spectral imaging for face recognition and the current challenges that hamper the widespread deployment of spectral sensors for face recognition. The reliability of conventional face recognition systems operating in the visible range is compromised by illumination changes, pose variations and spoof attacks. Recent works have reaped the benefits of spectral imaging to counter these limitations in surveillance activities (defence, airport security checks, etc.). However, the implementation of this technology for biometrics, is still in its infancy due to multiple reasons. We present an overview of the existing work in the domain of spectral imaging for face recognition, different types of modalities and their assessment, availability of public databases for sake of reproducible research as well as evaluation of algorithms, and recent advancements in the field, such as, the use of deep learning-based methods for recognizing faces from spectral images.
http://arxiv.org/abs/1807.05771
Vision-to-language tasks aim to integrate computer vision and natural language processing together, which has attracted the attention of many researchers. For typical approaches, they encode image into feature representations and decode it into natural language sentences. While they neglect high-level semantic concepts and subtle relationships between image regions and natural language elements. To make full use of these information, this paper attempt to exploit the text guided attention and semantic-guided attention (SA) to find the more correlated spatial information and reduce the semantic gap between vision and language. Our method includes two level attention networks. One is the text-guided attention network which is used to select the text-related regions. The other is SA network which is used to highlight the concept-related regions and the region-related concepts. At last, all these information are incorporated to generate captions or answers. Practically, image captioning and visual question answering experiments have been carried out, and the experimental results have shown the excellent performance of the proposed approach.
http://arxiv.org/abs/1905.12243
Learning portable neural networks is very essential for computer vision for the purpose that pre-trained heavy deep models can be well applied on edge devices such as mobile phones and micro sensors. Most existing deep neural network compression and speed-up methods are very effective for training compact deep models, when we can directly access the training dataset. However, training data for the given deep network are often unavailable due to some practice problems (e.g. privacy, legal issue, and transmission), and the architecture of the given network are also unknown except some interfaces. To this end, we propose a novel framework for training efficient deep neural networks by exploiting generative adversarial networks (GANs). To be specific, the pre-trained teacher networks are regarded as a fixed discriminator and the generator is utilized for derivating training samples which can obtain the maximum response on the discriminator. Then, an efficient network with smaller model size and computational complexity is trained using the generated data and the teacher network, simultaneously. Efficient student networks learned using the proposed Data-Free Learning (DAFL) method achieve 92.22% and 74.47% accuracies using ResNet-18 without any training data on the CIFAR-10 and CIFAR-100 datasets, respectively. Meanwhile, our student network obtains an 80.56% accuracy on the CelebA benchmark.
http://arxiv.org/abs/1904.01186
Brain-controlled unmanned aerial vehicle (uav) is a uav that can analyze human brain electrical signals through BCI to obtain flight commands. The research of brain-controlled uav can promote the integration of brain-computer and has a broad application prospect. At present, BCI still has some problems, such as limited recognition accuracy, limited recognition time and small number of recognition commands in the acquisition of control commands by analyzing eeg signals. Therefore, the control performance of the quadrotor which is controlled only by brain is not ideal. Based on the concept of Shared control, this paper designs an assistant controller using fuzzy PID control, and realizes the cooperative control between automatic control and brain control. By evaluating the current flight status and setting the switching rate, the switching mechanism of automatic control and brain control can be decided to improve the system control performance. Finally, a rectangular trajectory tracking control experiment of the same height is designed for small quadrotor to verify the algorithm.
http://arxiv.org/abs/1905.12240
Kernel methods have been successfully applied to the areas of pattern recognition and data mining. In this paper, we mainly discuss the issue of propagating labels in kernel space. A Kernel-Induced Label Propagation (Kernel-LP) framework by mapping is proposed for high-dimensional data classification using the most informative patterns of data in kernel space. The essence of Kernel-LP is to perform joint label propagation and adaptive weight learning in a transformed kernel space. That is, our Kernel-LP changes the task of label propagation from the commonly-used Euclidean space in most existing work to kernel space. The motivation of our Kernel-LP to propagate labels and learn the adaptive weights jointly by the assumption of an inner product space of inputs, i.e., the original linearly inseparable inputs may be mapped to be separable in kernel space. Kernel-LP is based on existing positive and negative LP model, i.e., the effects of negative label information are integrated to improve the label prediction power. Also, Kernel-LP performs adaptive weight construction over the same kernel space, so it can avoid the tricky process of choosing the optimal neighborhood size suffered in traditional criteria. Two novel and efficient out-of-sample approaches for our Kernel-LP to involve new test data are also presented, i.e., (1) direct kernel mapping and (2) kernel mapping-induced label reconstruction, both of which purely depend on the kernel matrix between training set and testing set. Owing to the kernel trick, our algorithms will be applicable to handle the high-dimensional real data. Extensive results on real datasets demonstrate the effectiveness of our approach.
http://arxiv.org/abs/1905.12236
The annihilating filter-based low-rank Hankel matrix approach (ALOHA) is one of the state-of-the-art compressed sensing approaches that directly interpolates the missing k-space data using low-rank Hankel matrix completion. The success of ALOHA is due to the concise signal representation in the k-space domain thanks to the duality between structured low-rankness in the k-space domain and the image domain sparsity. Inspired by the recent mathematical discovery that links convolutional neural networks to Hankel matrix decomposition using data-driven framelet basis, here we propose a fully data-driven deep learning algorithm for k-space interpolation. Our network can be also easily applied to non-Cartesian k-space trajectories by simply adding an additional regridding layer. Extensive numerical experiments show that the proposed deep learning method consistently outperforms the existing image-domain deep learning approaches.
http://arxiv.org/abs/1805.03779
In this paper, we present Hitachi and Paderborn University’s joint effort for automatic speech recognition (ASR) in a dinner party scenario. The main challenges of ASR systems for dinner party recordings obtained by multiple microphone arrays are (1) heavy speech overlaps, (2) severe noise and reverberation, (3) very natural conversational content, and possibly (4) insufficient training data. As an example of a dinner party scenario, we have chosen the data presented during the CHiME-5 speech recognition challenge, where the baseline ASR had a 73.3% word error rate (WER), and even the best performing system at the CHiME-5 challenge had a 46.1% WER. We extensively investigated a combination of the guided source separation-based speech enhancement technique and an already proposed strong ASR backend and found that a tight combination of these techniques provided substantial accuracy improvements. Our final system achieved WERs of 39.94% and 41.64% for the development and evaluation data, respectively, both of which are the best published results for the dataset. We also investigated with additional training data on the official small data in the CHiME-5 corpus to assess the intrinsic difficulty of this ASR task.
http://arxiv.org/abs/1905.12230
Convolution plays a crucial role in various applications in signal and image processing, analysis and recognition. It is also the main building block of convolution neural networks (CNNs). Designing appropriate convolution neural networks on manifold-structured point clouds can inherit and empower recent advances of CNNs to analyzing and processing point cloud data. However, one of the major challenges is to define a proper way to “sweep” filters through the point cloud as a natural generalization of the planar convolution and to reflect the point cloud’s geometry at the same time. In this paper, we consider generalizing convolution by adapting parallel transport on the point cloud. Inspired by a triangulated surface based method [Stefan C. Schonsheck, Bin Dong, and Rongjie Lai, arXiv:1805.07857.], we propose the Narrow-Band Parallel Transport Convolution (NPTC) using a specifically defined connection on a voxelized narrow-band approximation of point cloud data. With that, we further propose a deep convolutional neural network based on NPTC (called NPTC-net) for point cloud classification and segmentation. Comprehensive experiments show that the proposed NPTC-net achieves similar or better results than current state-of-the-art methods on point clouds classification and segmentation.
http://arxiv.org/abs/1905.12218
Brain controlled vehicle refers to the vehicle that obtains control commands by analyzing the driver’s EEG through Brain-Computer Interface (BCI). The research of brain controlled vehicles can not only promote the integration of brain machines, but also expand the range of activities and living ability of the disabled or some people with limited physical activity, so the research of brain controlled vehicles is of great significance and has broad application prospects. At present, BCI has some problems such as limited recognition accuracy, long recognition time and limited number of recognition commands in the process of analyzing EEG signals to obtain control commands. If only use the driver’s EEG signals to control the vehicle, the control performance is not ideal. Based on the concept of Shared control, this paper uses the fuzzy control (FC) to design an auxiliary controller to realize the cooperative control of automatic control and brain control. Designing a Shared controller which evaluates the current vehicle status and decides the switching mechanism between automatic control and brain control to improve the system control performance. Finally, based on the joint simulation platform of Carsim and MATLAB, with the simulated brain control signals, the designed experiment verifies that the control performance of the brain control vehicle can be improved by adding the auxiliary controller.
http://arxiv.org/abs/1905.13044
In this paper, we consider recommender systems with side information in the form of graphs. Existing collaborative filtering algorithms mainly utilize only immediate neighborhood information and have a hard time taking advantage of deeper neighborhoods beyond 1-2 hops. The main caveat of exploiting deeper graph information is the rapidly growing time and space complexity when incorporating information from these neighborhoods. In this paper, we propose using Graph DNA, a novel Deep Neighborhood Aware graph encoding algorithm, for exploiting deeper neighborhood information. DNA encoding computes approximate deep neighborhood information in linear time using Bloom filters, a space-efficient probabilistic data structure and results in a per-node encoding that is logarithmic in the number of nodes in the graph. It can be used in conjunction with both feature-based and graph-regularization-based collaborative filtering algorithms. Graph DNA has the advantages of being memory and time efficient and providing additional regularization when compared to directly using higher order graph information. We conduct experiments on real-world datasets, showing graph DNA can be easily used with 4 popular collaborative filtering algorithms and consistently leads to a performance boost with little computational and memory overhead.
http://arxiv.org/abs/1905.12217
We compute the transition probability between two learning tasks, and show that it decomposes into two factors. The first depends on the geometry of the loss landscape of a model trained on each task, independent of any particular model used. This is related to an information theoretic distance function, but is insufficient to predict success in transfer learning, as nearby tasks can be unreachable via fine-tuning. The second factor depends on the ease of traversing the path between two tasks. With this dynamic component, we derive strict lower bounds on the complexity necessary to learn a task starting from the solution to another, which is one of the most common forms of transfer learning.
http://arxiv.org/abs/1810.02440
Whatever information a Deep Neural Network has gleaned from past data is encoded in its weights. How this information affects the response of the network to future data is largely an open question. In fact, even how to define and measure information in a network is still not settled. We introduce the notion of Information in the Weights as the optimal trade-off between accuracy of the network and complexity of the weights, relative to a prior. Depending on the prior, the definition reduces to known information measures such as Shannon Mutual Information and Fisher Information, but affords added flexibility that enables us to relate it to generalization, via the PAC-Bayes bound, and to invariance. This relation hinges not only on the architecture of the model, but surprisingly on how it is trained. We then introduce a notion of effective information in the activations, which are deterministic functions of future inputs, resolving inconsistencies in prior work. We relate this to the Information in the Weights, and use this result to show that models of low complexity not only generalize better, but are bound to learn invariant representations of future inputs.
http://arxiv.org/abs/1905.12213
Can the success of reinforcement learning methods for combinatorial optimization problems be extended to multi-robot scheduling problems in stochastic contexts? Three issues are particularly important in this context: quality of the resulting decisions, scalability, and transferability. To achieve these ends we generalize the concept of clique potential to stochastic clique potential. We extend a mean field inference fixed point iteration with this new concept and use it to modify thestructure2vec method. We next propose a new reinforcement learning framework combining a graph representation of the problem and a consensus auction inspired by heuristics in the problem domain. This representation enables transferability in terms of the number of robots. Sequential encoding of information through multiple layers of our extended structure2vec results in 96% optimal performance of the learned heuristics. While training tractability is inherited from single robot methods in the literature, use of a multi-robot consensus auction-based relaxation of the maximum operation in the Bellman optimality equation allows for scalable selection of actions in the fitted Q-iteration. We apply our framework to multi-robot reward collection (MRRC) problems in stochastic environments with linear or non-linear rewards. In stochastic environments with non-linear rewards, the new method achieves 20% superior performance relative to the popular sequential greedy assignment (SGA) algorithm. Linear scalability in terms of training is achieved and demonstrated. Transferability is demonstrated by the use of a heuristic trained with three robots that continues to achieve 95% optimal performance when applied to problems with various numbers of robots. We further mention the results obtained when extending the approach to identical parallel machine scheduling(IPMS) problems.
http://arxiv.org/abs/1905.12204
A type description is a succinct noun compound which helps human and machines to quickly grasp the informative and distinctive information of an entity. Entities in most knowledge graphs (KGs) still lack such descriptions, thus calling for automatic methods to supplement such information. However, existing generative methods either overlook the grammatical structure or make factual mistakes in generated texts. To solve these problems, we propose a head-modifier template-based method to ensure the readability and data fidelity of generated type descriptions. We also propose a new dataset and two automatic metrics for this task. Experiments show that our method improves substantially compared with baselines and achieves state-of-the-art performance on both datasets.
http://arxiv.org/abs/1905.12198
Autonomous driving in a crowded environment, e.g., a busy traffic intersection, is an unsolved challenge for robotics. The robot vehicle must contend with a dynamic and partially observable environment, noisy sensors, and many agents. A principled approach is to formalize it as a Partially Observable Markov Decision Process (POMDP) and solve it through online belief-tree search. To handle a large crowd and achieve real-time performance in this very challenging setting, we propose LeTS-Drive, which integrates online POMDP planning and deep learning. It consists of two phases. In the offline phase, we learn a policy and the corresponding value function by imitating the belief tree search. In the online phase, the learned policy and value function guide the belief tree search. LeTS-Drive leverages the robustness of planning and the runtime efficiency of learning to enhance the performance of both. Experimental results in simulation show that LeTS-Drive outperforms either planning or imitation learning alone and develops sophisticated driving skills.
http://arxiv.org/abs/1905.12197
We reveal a complete set of constraints that need to be imposed on a set of 3-by-3 matrices to ensure that the matrices represent genuine homographies associated with multiple planes between two views. We also show how to exploit the constraints to obtain more accurate estimates of homography matrices between two views. Our study resolves a long-standing research question and provides a fresh perspective and a more in-depth understanding of the multiple homography estimation task.
http://arxiv.org/abs/1805.02352
This paper addresses the problem of Multi-robot Coverage Path Planning (MCPP) for unknown environments in the presence of robot failures. Unexpected robot failures can seriously degrade the performance of a robot team and in extreme cases jeopardize the overall operation. Therefore, this paper presents a distributed algorithm, called Cooperative Autonomy for Resilience and Efficiency (CARE), which not only provides resilience to the robot team against failures of individual robots, but also improves the overall efficiency of operation via event-driven replanning. The algorithm uses distributed Discrete Event Supervisors (DESs), which trigger games between a set of feasible players in the event of a robot failure or idling, to make collaborative decisions for task reallocations. The game-theoretic structure is built using Potential Games, where the utility of each player is aligned with a shared objective function for all players. The algorithm has been validated in various complex scenarios on a high-fidelity robotic simulator, and the results demonstrate that the team achieves complete coverage under failures, reduced coverage time, and faster target discovery as compared to three alternative methods.
http://arxiv.org/abs/1905.12191
We study the problem of tracking multiple moving targets using a team of mobile robots. Each robot has a set of motion primitives to choose from in order to collectively maximize the number of targets tracked or the total quality of tracking. Our focus is on scenarios where communication is limited and the robots have limited time to share information with their neighbors. As a result, we seek distributed algorithms that can find solutions in bounded amount of time. We present two algorithms: (1) a greedy algorithm that is guaranteed finds a $2$-approximation to the optimal (centralized) solution albeit requiring $|R|$ communication rounds in the worst-case, where $|R|$ denotes the number of robots; and (2) a local algorithm that finds a $\mathcal{O}\left((1+\epsilon)(1+1/h)\right)$-approximation algorithm in $\mathcal{O}(h\log 1/\epsilon)$ communication rounds. Here, $h$ and $\epsilon$ are parameters that allow the user to trade-off the solution quality with communication time. In addition to theoretical results, we present empirical evaluation including comparisons with centralized optimal solutions.
http://arxiv.org/abs/1812.11172
Weakly-supervised semantic segmentation aims to assign each pixel a semantic category under weak supervisions, such as image-level tags. Most of existing weakly-supervised semantic segmentation methods do not use any feedback from segmentation output and can be considered as open-loop systems. They are prone to accumulated errors because of the static seeds and the sensitive structure information. In this paper, we propose a generic self-adaptation mechanism for existing weakly-supervised semantic segmentation methods by introducing two feedback chains, thus constituting a closed-loop system. Specifically, the first chain iteratively produces dynamic seeds by incorporating cross-image structure information, whereas the second chain further expands seed regions by a customized random walk process to reconcile inner-image structure information characterized by superpixels. Experiments on PASCAL VOC 2012 suggest that our network outperforms state-of-the-art methods with significantly less computational and memory burden.
http://arxiv.org/abs/1905.12190
In this paper, we introduce DRCD (Delta Reading Comprehension Dataset), an open domain traditional Chinese machine reading comprehension (MRC) dataset. This dataset aimed to be a standard Chinese machine reading comprehension dataset, which can be a source dataset in transfer learning. The dataset contains 10,014 paragraphs from 2,108 Wikipedia articles and 30,000+ questions generated by annotators. We build a baseline model that achieves an F1 score of 89.59%. F1 score of Human performance is 93.30%.
http://arxiv.org/abs/1806.00920
In human conversations, due to their personalities in mind, people can easily carry out and maintain the conversations. Giving conversational context with persona information to a chatbot, how to exploit the information to generate diverse and sustainable conversations is still a non-trivial task. Previous work on persona-based conversational models successfully make use of predefined persona information and have shown great promise in delivering more realistic responses. And they all learn with the assumption that given a source input, there is only one target response. However, in human conversations, there are massive appropriate responses to a given input message. In this paper, we propose a memory-augmented architecture to exploit persona information from context and incorporate a conditional variational autoencoder model together to generate diverse and sustainable conversations. We evaluate the proposed model on a benchmark persona-chat dataset. Both automatic and human evaluations show that our model can deliver more diverse and more engaging persona-based responses than baseline approaches.
http://arxiv.org/abs/1905.12188
General intelligence, the ability to solve arbitrary solvable problems, is supposed by many to be artificially constructible. Narrow intelligence, the ability to solve a given particularly difficult problem, has seen impressive recent development. Notable examples include self-driving cars, Go engines, image classifiers, and translators. Artificial General Intelligence (AGI) presents dangers that narrow intelligence does not: if something smarter than us across every domain were indifferent to our concerns, it would be an existential threat to humanity, just as we threaten many species despite no ill will. Even the theory of how to maintain the alignment of an AGI’s goals with our own has proven highly elusive. We present the first algorithm we are aware of for asymptotically unambitious AGI, where “unambitiousness” includes not seeking arbitrary power. Thus, we identify an exception to the Instrumental Convergence Thesis, which is roughly that by default, an AGI would seek power, including over us.
http://arxiv.org/abs/1905.12186
Visual data, such as an image or a sequence of video frames, is often naturally represented as a point set. In this paper, we consider the fundamental problem of finding a nearest set from a collection of sets, to a query set. This problem has obvious applications in large-scale visual retrieval and recognition, and also in applied fields beyond computer vision. One challenge stands out in solving the problem—set representation and measure of similarity. Particularly, the query set and the sets in dataset collection can have varying cardinalities. The training collection is large enough such that linear scan is impractical. We propose a simple representation scheme that encodes both statistical and structural information of the sets. The derived representations are integrated in a kernel framework for flexible similarity measurement. For the query set process, we adopt a learning-to-hash pipeline that turns the kernel representations into hash bits based on simple learners, using multiple kernel learning. Experiments on two visual retrieval datasets show unambiguously that our set-to-set hashing framework outperforms prior methods that do not take the set-to-set search setting.
http://arxiv.org/abs/1711.00888
Volumetric (4D) performance capture is fundamental for AR/VR content generation. Whereas previous work in 4D performance capture has shown impressive results in studio settings, the technology is still far from being accessible to a typical consumer who, at best, might own a single RGBD sensor. Thus, in this work, we propose a method to synthesize free viewpoint renderings using a single RGBD camera. The key insight is to leverage previously seen “calibration” images of a given user to extrapolate what should be rendered in a novel viewpoint from the data available in the sensor. Given these past observations from multiple viewpoints, and the current RGBD image from a fixed view, we propose an end-to-end framework that fuses both these data sources to generate novel renderings of the performer. We demonstrate that the method can produce high fidelity images, and handle extreme changes in subject pose and camera viewpoints. We also show that the system generalizes to performers not seen in the training data. We run exhaustive experiments demonstrating the effectiveness of the proposed semi-parametric model (i.e. calibration images available to the neural network) compared to other state of the art machine learned solutions. Further, we compare the method with more traditional pipelines that employ multi-view capture. We show that our framework is able to achieve compelling results, with substantially less infrastructure than previously required.
http://arxiv.org/abs/1905.12162
Most existing super-resolution methods do not perform well in real scenarios due to lack of realistic training data and information loss of the model input. To solve the first problem, we propose a new pipeline to generate realistic training data by simulating the imaging process of digital cameras. And to remedy the information loss of the input, we develop a dual convolutional neural network to exploit the originally captured radiance information in raw images. In addition, we propose to learn a spatially-variant color transformation which helps more effective color corrections. Extensive experiments demonstrate that super-resolution with raw data helps recover fine details and clear structures, and more importantly, the proposed network and data generation pipeline achieve superior results for single image super-resolution in real scenarios.
http://arxiv.org/abs/1905.12156
Integrating logical reasoning within deep learning architectures has been a major goal of modern AI systems. In this paper, we propose a new direction toward this goal by introducing a differentiable (smoothed) maximum satisfiability (MAXSAT) solver that can be integrated into the loop of larger deep learning systems. Our (approximate) solver is based upon a fast coordinate descent approach to solving the semidefinite program (SDP) associated with the MAXSAT problem. We show how to analytically differentiate through the solution to this SDP and efficiently solve the associated backward pass. We demonstrate that by integrating this solver into end-to-end learning systems, we can learn the logical structure of challenging problems in a minimally supervised fashion. In particular, we show that we can learn the parity function using single-bit supervision (a traditionally hard task for deep networks) and learn how to play 9x9 Sudoku solely from examples. We also solve a “visual Sudok” problem that maps images of Sudoku puzzles to their associated logical solutions by combining our MAXSAT solver with a traditional convolutional architecture. Our approach thus shows promise in integrating logical structures within deep learning.
http://arxiv.org/abs/1905.12149