Exploration in an unknown environment is the core functionality for mobile robots. Learning-based exploration methods, including convolutional neural networks, provide excellent strategies without human-designed logic for the feature extraction. But the conventional supervised learning algorithms cost lots of efforts on the labeling work of datasets inevitably. Scenes not included in the training set are mostly unrecognized either. We propose a deep reinforcement learning method for the exploration of mobile robots in an indoor environment with the depth information from an RGB-D sensor only. Based on the Deep Q-Network framework, the raw depth image is taken as the only input to estimate the Q values corresponding to all moving commands. The training of the network weights is end-to-end. In arbitrarily constructed simulation environments, we show that the robot can be quickly adapted to unfamiliar scenes without any man-made labeling. Besides, through analysis of receptive fields of feature representations, deep reinforcement learning motivates the convolutional networks to estimate the traversability of the scenes. The test results are compared with the exploration strategies separately based on deep learning or reinforcement learning. Even trained only in the simulated environment, experimental results in real-world environment demonstrate that the cognitive ability of robot controller is dramatically improved compared with the supervised method. We believe it is the first time that raw sensor information is used to build cognitive exploration strategy for mobile robots through end-to-end deep reinforcement learning.

Click to Read Paper
Quantum circuit Born machines are generative models which represent the probability distribution of classical dataset as quantum pure states. Computational complexity considerations of the quantum sampling problem suggest that the quantum circuits exhibit stronger expressibility compared to classical neural networks. One can efficiently draw samples from the quantum circuits via projective measurements on qubits. However, similar to the leading implicit generative models in deep learning, such as the generative adversarial networks, the quantum circuits cannot provide the likelihood of the generated samples, which poses a challenge to the training. We devise an efficient gradient-based learning algorithm for the quantum circuit Born machine by minimizing the kerneled maximum mean discrepancy loss. We simulated generative modeling of the Bars-and-Stripes dataset and Gaussian mixture distributions using deep quantum circuits. Our experiments show the importance of circuit depth and gradient-based optimization algorithm. The proposed learning algorithm is runnable on near-term quantum device and can exhibit quantum advantages for generative modeling.

* 9 pages, 7 figures, Github page for code https://github.com/GiggleLiu/QuantumCircuitBornMachine
Click to Read Paper
Detection of arbitrarily rotated objects is a challenging task due to the difficulties of locating the multi-angle objects and separating them effectively from the background. The existing methods are not robust to angle varies of the objects because of the use of traditional bounding box, which is a rotation variant structure for locating rotated objects. In this article, a new detection method is proposed which applies the newly defined rotatable bounding box (RBox). The proposed detector (DRBox) can effectively handle the situation where the orientation angles of the objects are arbitrary. The training of DRBox forces the detection networks to learn the correct orientation angle of the objects, so that the rotation invariant property can be achieved. DRBox is tested to detect vehicles, ships and airplanes on satellite images, compared with Faster R-CNN and SSD, which are chosen as the benchmark of the traditional bounding box based methods. The results shows that DRBox performs much better than traditional bounding box based methods do on the given tasks, and is more robust against rotation of input image and target objects. Besides, results show that DRBox correctly outputs the orientation angles of the objects, which is very useful for locating multi-angle objects efficiently. The code and models are available at https://github.com/liulei01/DRBox.

Click to Read Paper
In this work, we address the face parsing task with a Fully-Convolutional continuous CRF Neural Network (FC-CNN) architecture. In contrast to previous face parsing methods that apply region-based subnetwork hundreds of times, our FC-CNN is fully convolutional with high segmentation accuracy. To achieve this goal, FC-CNN integrates three subnetworks, a unary network, a pairwise network and a continuous Conditional Random Field (C-CRF) network into a unified framework. The high-level semantic information and low-level details across different convolutional layers are captured by the convolutional and deconvolutional structures in the unary network. The semantic edge context is learnt by the pairwise network branch to construct pixel-wise affinity. Based on a differentiable superpixel pooling layer and a differentiable C-CRF layer, the unary network and pairwise network are combined via a novel continuous CRF network to achieve spatial consistency in both training and test procedure of a deep neural network. Comprehensive evaluations on LFW-PL and HELEN datasets demonstrate that FC-CNN achieves better performance over the other state-of-arts for accurate face labeling on challenging images.

Click to Read Paper
We propose a simple yet effective model for Single Image Super-Resolution (SISR), by combining the merits of Residual Learning and Convolutional Sparse Coding (RL-CSC). Our model is inspired by the Learned Iterative Shrinkage-Threshold Algorithm (LISTA). We extend LISTA to its convolutional version and build the main part of our model by strictly following the convolutional form, which improves the network's interpretability. Specifically, the convolutional sparse codings of input feature maps are learned in a recursive manner, and high-frequency information can be recovered from these CSCs. More importantly, residual learning is applied to alleviate the training difficulty when the network goes deeper. Extensive experiments on benchmark datasets demonstrate the effectiveness of our method. RL-CSC (30 layers) outperforms several recent state-of-the-arts, e.g., DRRN (52 layers) and MemNet (80 layers) in both accuracy and visual qualities. Codes and more results are available at https://github.com/axzml/RL-CSC.

* 10 pages, 8 figures, 4 tables
Click to Read Paper
Deep learning has emerged as a powerful machine learning technique that learns multiple layers of representations or features of the data and produces state-of-the-art prediction results. Along with the success of deep learning in many other application domains, deep learning is also popularly used in sentiment analysis in recent years. This paper first gives an overview of deep learning and then provides a comprehensive survey of its current applications in sentiment analysis.

* 34 pages, 9 figures, 2 tables
Click to Read Paper
This paper concerns open-world classification, where the classifier not only needs to classify test examples into seen classes that have appeared in training but also reject examples from unseen or novel classes that have not appeared in training. Specifically, this paper focuses on discovering the hidden unseen classes of the rejected examples. Clearly, without prior knowledge this is difficult. However, we do have the data from the seen training classes, which can tell us what kind of similarity/difference is expected for examples from the same class or from different classes. It is reasonable to assume that this knowledge can be transferred to the rejected examples and used to discover the hidden unseen classes in them. This paper aims to solve this problem. It first proposes a joint open classification model with a sub-model for classifying whether a pair of examples belongs to the same or different classes. This sub-model can serve as a distance function for clustering to discover the hidden classes of the rejected examples. Experimental results show that the proposed model is highly promising.

Click to Read Paper
Traditional supervised learning makes the closed-world assumption that the classes appeared in the test data must have appeared in training. This also applies to text learning or text classification. As learning is used increasingly in dynamic open environments where some new/test documents may not belong to any of the training classes, identifying these novel documents during classification presents an important problem. This problem is called open-world classification or open classification. This paper proposes a novel deep learning based approach. It outperforms existing state-of-the-art techniques dramatically.

* accepted at EMNLP 2017
Click to Read Paper
In this paper we focus on developing a control algorithm for multi-terrain tracked robots with flippers using a reinforcement learning (RL) approach. The work is based on the deep deterministic policy gradient (DDPG) algorithm, proven to be very successful in simple simulation environments. The algorithm works in an end-to-end fashion in order to control the continuous position of the flippers. This end-to-end approach makes it easy to apply the controller to a wide array of circumstances, but the huge flexibility comes to the cost of an increased difficulty of solution. The complexity of the task is enlarged even more by the fact that real multi-terrain robots move in partially observable environments. Notwithstanding these complications, being able to smoothly control a multi-terrain robot can produce huge benefits in impaired people daily lives or in search and rescue situations.

* 12 pages, single column, submitted to International Journal of Robotics and Automation (IJRA)
Click to Read Paper
We present a learning-based mapless motion planner by taking the sparse 10-dimensional range findings and the target position with respect to the mobile robot coordinate frame as input and the continuous steering commands as output. Traditional motion planners for mobile ground robots with a laser range sensor mostly depend on the obstacle map of the navigation environment where both the highly precise laser sensor and the obstacle map building work of the environment are indispensable. We show that, through an asynchronous deep reinforcement learning method, a mapless motion planner can be trained end-to-end without any manually designed features and prior demonstrations. The trained planner can be directly applied in unseen virtual and real environments. The experiments show that the proposed mapless motion planner can navigate the nonholonomic mobile robot to the desired targets without colliding with any obstacles.

* video: https://www.youtube.com/watch?v=9AOIwBYIBbs, 6 pages, 9 figures, to appear in he 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2017), final submission version
Click to Read Paper
This paper makes a focused contribution to supervised aspect extraction. It shows that if the system has performed aspect extraction from many past domains and retained their results as knowledge, Conditional Random Fields (CRF) can leverage this knowledge in a lifelong learning manner to extract in a new domain markedly better than the traditional CRF without using this prior knowledge. The key innovation is that even after CRF training, the model can still improve its extraction with experiences in its applications.

* Accepted at ACL 2017. arXiv admin note: text overlap with arXiv:1612.07940
Click to Read Paper
Compact and discriminative visual codebooks are preferred in many visual recognition tasks. In the literature, a number of works have taken the approach of hierarchically merging visual words of an initial large-sized codebook, but implemented this approach with different merging criteria. In this work, we propose a single probabilistic framework to unify these merging criteria, by identifying two key factors: the function used to model class-conditional distribution and the method used to estimate the distribution parameters. More importantly, by adopting new distribution functions and/or parameter estimation methods, our framework can readily produce a spectrum of novel merging criteria. Three of them are specifically focused in this work. In the first criterion, we adopt the multinomial distribution with Bayesian method; In the second criterion, we integrate Gaussian distribution with maximum likelihood parameter estimation. In the third criterion, which shows the best merging performance, we propose a max-margin-based parameter estimation method and apply it with multinomial distribution. Extensive experimental study is conducted to systematically analyse the performance of the above three criteria and compare them with existing ones. As demonstrated, the best criterion obtained in our framework achieves the overall best merging performance among the comparable merging criteria developed in the literature.

Click to Read Paper
We consider the following signal recovery problem: given a measurement matrix $\Phi\in \mathbb{R}^{n\times p}$ and a noisy observation vector $c\in \mathbb{R}^{n}$ constructed from $c = \Phi\theta^* + \epsilon$ where $\epsilon\in \mathbb{R}^{n}$ is the noise vector whose entries follow i.i.d. centered sub-Gaussian distribution, how to recover the signal $\theta^*$ if $D\theta^*$ is sparse {\rca under a linear transformation} $D\in\mathbb{R}^{m\times p}$? One natural method using convex optimization is to solve the following problem: $$\min_{\theta} {1\over 2}\|\Phi\theta - c\|^2 + \lambda\|D\theta\|_1.$$ This paper provides an upper bound of the estimate error and shows the consistency property of this method by assuming that the design matrix $\Phi$ is a Gaussian random matrix. Specifically, we show 1) in the noiseless case, if the condition number of $D$ is bounded and the measurement number $n\geq \Omega(s\log(p))$ where $s$ is the sparsity number, then the true solution can be recovered with high probability; and 2) in the noisy case, if the condition number of $D$ is bounded and the measurement increases faster than $s\log(p)$, that is, $s\log(p)=o(n)$, the estimate error converges to zero with probability 1 when $p$ and $s$ go to infinity. Our results are consistent with those for the special case $D=\bold{I}_{p\times p}$ (equivalently LASSO) and improve the existing analysis. The condition number of $D$ plays a critical role in our analysis. We consider the condition numbers in two cases including the fused LASSO and the random graph: the condition number in the fused LASSO case is bounded by a constant, while the condition number in the random graph case is bounded with high probability if $m\over p$ (i.e., $#text{edge}\over #text{vertex}$) is larger than a certain constant. Numerical simulations are consistent with our theoretical results.

* 26 pages, 3 figures, ICML2013
Click to Read Paper
Generative Adversarial Networks (GANs) have shown great capacity on image generation, in which a discriminative model guides the training of a generative model to construct images that resemble real images. Recently, GANs have been extended from generating images to generating sequences (e.g., poems, music and codes). Existing GANs on sequence generation mainly focus on general sequences, which are grammar-free. In many real-world applications, however, we need to generate sequences in a formal language with the constraint of its corresponding grammar. For example, to test the performance of a database, one may want to generate a collection of SQL queries, which are not only similar to the queries of real users, but also follow the SQL syntax of the target database. Generating such sequences is highly challenging because both the generator and discriminator of GANs need to consider the structure of the sequences and the given grammar in the formal language. To address these issues, we study the problem of syntax-aware sequence generation with GANs, in which a collection of real sequences and a set of pre-defined grammatical rules are given to both discriminator and generator. We propose a novel GAN framework, namely TreeGAN, to incorporate a given Context-Free Grammar (CFG) into the sequence generation process. In TreeGAN, the generator employs a recurrent neural network (RNN) to construct a parse tree. Each generated parse tree can then be translated to a valid sequence of the given grammar. The discriminator uses a tree-structured RNN to distinguish the generated trees from real trees. We show that TreeGAN can generate sequences for any CFG and its generation fully conforms with the given syntax. Experiments on synthetic and real data sets demonstrated that TreeGAN significantly improves the quality of the sequence generation in context-free languages.

* IEEE International Conference on Data Mining (ICDM'18)
Click to Read Paper
Deep learning approaches for sentiment classification do not fully exploit sentiment linguistic knowledge. In this paper, we propose a Multi-sentiment-resource Enhanced Attention Network (MEAN) to alleviate the problem by integrating three kinds of sentiment linguistic knowledge (e.g., sentiment lexicon, negation words, intensity words) into the deep neural network via attention mechanisms. By using various types of sentiment resources, MEAN utilizes sentiment-relevant information from different representation subspaces, which makes it more effective to capture the overall semantics of the sentiment, negation and intensity words for sentiment prediction. The experimental results demonstrate that MEAN has robust superiority over strong competitors.

Click to Read Paper
Convolutional neural networks (CNNs) can be applied to graph similarity matching, in which case they are called graph CNNs. Graph CNNs are attracting increasing attention due to their effectiveness and efficiency. However, the existing convolution approaches focus only on regular data forms and require the transfer of the graph or key node neighborhoods of the graph into the same fixed form. During this transfer process, structural information of the graph can be lost, and some redundant information can be incorporated. To overcome this problem, we propose the disordered graph convolutional neural network (DGCNN) based on the mixed Gaussian model, which extends the CNN by adding a preprocessing layer called the disordered graph convolutional layer (DGCL). The DGCL uses a mixed Gaussian function to realize the mapping between the convolution kernel and the nodes in the neighborhood of the graph. The output of the DGCL is the input of the CNN. We further implement a backward-propagation optimization process of the convolutional layer by which we incorporate the feature-learning model of the irregular node neighborhood structure into the network. Thereafter, the optimization of the convolution kernel becomes part of the neural network learning process. The DGCNN can accept arbitrary scaled and disordered neighborhood graph structures as the receptive fields of CNNs, which reduces information loss during graph transformation. Finally, we perform experiments on multiple standard graph datasets. The results show that the proposed method outperforms the state-of-the-art methods in graph classification and retrieval.

* 16 pages,8 figures
Click to Read Paper
Optimizing deep neural networks (DNNs) often suffers from the ill-conditioned problem. We observe that the scaling-based weight space symmetry property in rectified nonlinear network will cause this negative effect. Therefore, we propose to constrain the incoming weights of each neuron to be unit-norm, which is formulated as an optimization problem over Oblique manifold. A simple yet efficient method referred to as projection based weight normalization (PBWN) is also developed to solve this problem. PBWN executes standard gradient updates, followed by projecting the updated weight back to Oblique manifold. This proposed method has the property of regularization and collaborates well with the commonly used batch normalization technique. We conduct comprehensive experiments on several widely-used image datasets including CIFAR-10, CIFAR-100, SVHN and ImageNet for supervised learning over the state-of-the-art convolutional neural networks, such as Inception, VGG and residual networks. The results show that our method is able to improve the performance of DNNs with different architectures consistently. We also apply our method to Ladder network for semi-supervised learning on permutation invariant MNIST dataset, and our method outperforms the state-of-the-art methods: we obtain test errors as 2.52%, 1.06%, and 0.91% with only 20, 50, and 100 labeled samples, respectively.

* 12 pages, 3 figures
Click to Read Paper
Semantic segmentation of functional magnetic resonance imaging (fMRI) makes great sense for pathology diagnosis and decision system of medical robots. The multi-channel fMRI provides more information of the pathological features. But the increased amount of data causes complexity in feature detections. This paper proposes a principal component analysis (PCA)-aided fully convolutional network to particularly deal with multi-channel fMRI. We transfer the learned weights of contemporary classification networks to the segmentation task by fine-tuning. The results of the convolutional network are compared with various methods e.g. k-NN. A new labeling strategy is proposed to solve the semantic segmentation problem with unclear boundaries. Even with a small-sized training dataset, the test results demonstrate that our model outperforms other pathological feature detection methods. Besides, its forward inference only takes 90 milliseconds for a single set of fMRI data. To our knowledge, this is the first time to realize pixel-wise labeling of multi-channel magnetic resonance image using FCN.

* ICAR 2017 - 18th International Conference on Advanced Robotics, Best Student Paper Award, 6 figures
Click to Read Paper
In this paper, we propose a hierarchical deep reinforcement learning (DRL)-based AutoML framework, AutoQB, to automatically explore the design space of channel-level network quantization and binarization for hardware-friendly deep learning on mobile devices. Compared to prior DDPG-based quantization techniques, on the various CNN models, AutoQB automatically achieves the same inference accuracy by $\sim79\%$ less computing overhead, or improves the inference accuracy by $\sim2\%$ with the same computing cost.

* 10 pages, 12 figures
Click to Read Paper
We propose in this work RBM-SVGD, a stochastic version of Stein Variational Gradient Descent (SVGD) method for efficiently sampling from a given probability measure and thus useful for Bayesian inference. The method is to apply the Random Batch Method (RBM) for interacting particle systems proposed by Jin et al to the interacting particle systems in SVGD. While keeping the behaviors of SVGD, it reduces the computational cost, especially when the interacting kernel has long range. Numerical examples verify the efficiency of this new version of SVGD.

Click to Read Paper