Paper Group ANR 413
Conditional Generative Adversarial Networks for Emoji Synthesis with Word Embedding Manipulation. Linearly-Recurrent Autoencoder Networks for Learning Dynamics. Learning 6-DOF Grasping Interaction via Deep Geometry-aware 3D Representations. Convolutional Neural Networks for Non-iterative Reconstruction of Compressively Sensed Images. Algebraic Imag …
Conditional Generative Adversarial Networks for Emoji Synthesis with Word Embedding Manipulation
| Title | Conditional Generative Adversarial Networks for Emoji Synthesis with Word Embedding Manipulation |
| Authors | Dianna Radpour, Vivek Bheda |
| Abstract | Emojis have become a very popular part of daily digital communication. Their appeal comes largely in part due to their ability to capture and elicit emotions in a more subtle and nuanced way than just plain text is able to. In line with recent advances in the field of deep learning, there are far reaching implications and applications that generative adversarial networks (GANs) can have for image generation. In this paper, we present a novel application of deep convolutional GANs (DC-GANs) with an optimized training procedure. We show that via incorporation of word embeddings conditioned on Google’s word2vec model into the network, the generator is able to synthesize highly realistic emojis that are virtually identical to the real ones. |
| Tasks | Image Generation, Word Embeddings |
| Published | 2017-12-12 |
| URL | http://arxiv.org/abs/1712.04421v3 |
| http://arxiv.org/pdf/1712.04421v3.pdf | |
| PWC | https://paperswithcode.com/paper/conditional-generative-adversarial-networks |
| Repo | |
| Framework | |
Linearly-Recurrent Autoencoder Networks for Learning Dynamics
| Title | Linearly-Recurrent Autoencoder Networks for Learning Dynamics |
| Authors | Samuel E. Otto, Clarence W. Rowley |
| Abstract | This paper describes a method for learning low-dimensional approximations of nonlinear dynamical systems, based on neural-network approximations of the underlying Koopman operator. Extended Dynamic Mode Decomposition (EDMD) provides a useful data-driven approximation of the Koopman operator for analyzing dynamical systems. This paper addresses a fundamental problem associated with EDMD: a trade-off between representational capacity of the dictionary and over-fitting due to insufficient data. A new neural network architecture combining an autoencoder with linear recurrent dynamics in the encoded state is used to learn a low-dimensional and highly informative Koopman-invariant subspace of observables. A method is also presented for balanced model reduction of over-specified EDMD systems in feature space. Nonlinear reconstruction using partially linear multi-kernel regression aims to improve reconstruction accuracy from the low-dimensional state when the data has complex but intrinsically low-dimensional structure. The techniques demonstrate the ability to identify Koopman eigenfunctions of the unforced Duffing equation, create accurate low-dimensional models of an unstable cylinder wake flow, and make short-time predictions of the chaotic Kuramoto-Sivashinsky equation. |
| Tasks | |
| Published | 2017-12-04 |
| URL | http://arxiv.org/abs/1712.01378v2 |
| http://arxiv.org/pdf/1712.01378v2.pdf | |
| PWC | https://paperswithcode.com/paper/linearly-recurrent-autoencoder-networks-for |
| Repo | |
| Framework | |
Learning 6-DOF Grasping Interaction via Deep Geometry-aware 3D Representations
| Title | Learning 6-DOF Grasping Interaction via Deep Geometry-aware 3D Representations |
| Authors | Xinchen Yan, Jasmine Hsu, Mohi Khansari, Yunfei Bai, Arkanath Pathak, Abhinav Gupta, James Davidson, Honglak Lee |
| Abstract | This paper focuses on the problem of learning 6-DOF grasping with a parallel jaw gripper in simulation. We propose the notion of a geometry-aware representation in grasping based on the assumption that knowledge of 3D geometry is at the heart of interaction. Our key idea is constraining and regularizing grasping interaction learning through 3D geometry prediction. Specifically, we formulate the learning of deep geometry-aware grasping model in two steps: First, we learn to build mental geometry-aware representation by reconstructing the scene (i.e., 3D occupancy grid) from RGBD input via generative 3D shape modeling. Second, we learn to predict grasping outcome with its internal geometry-aware representation. The learned outcome prediction model is used to sequentially propose grasping solutions via analysis-by-synthesis optimization. Our contributions are fourfold: (1) To best of our knowledge, we are presenting for the first time a method to learn a 6-DOF grasping net from RGBD input; (2) We build a grasping dataset from demonstrations in virtual reality with rich sensory and interaction annotations. This dataset includes 101 everyday objects spread across 7 categories, additionally, we propose a data augmentation strategy for effective learning; (3) We demonstrate that the learned geometry-aware representation leads to about 10 percent relative performance improvement over the baseline CNN on grasping objects from our dataset. (4) We further demonstrate that the model generalizes to novel viewpoints and object instances. |
| Tasks | 3D Shape Modeling, Data Augmentation |
| Published | 2017-08-24 |
| URL | http://arxiv.org/abs/1708.07303v4 |
| http://arxiv.org/pdf/1708.07303v4.pdf | |
| PWC | https://paperswithcode.com/paper/learning-6-dof-grasping-interaction-via-deep |
| Repo | |
| Framework | |
Convolutional Neural Networks for Non-iterative Reconstruction of Compressively Sensed Images
| Title | Convolutional Neural Networks for Non-iterative Reconstruction of Compressively Sensed Images |
| Authors | Suhas Lohit, Kuldeep Kulkarni, Ronan Kerviche, Pavan Turaga, Amit Ashok |
| Abstract | Traditional algorithms for compressive sensing recovery are computationally expensive and are ineffective at low measurement rates. In this work, we propose a data driven non-iterative algorithm to overcome the shortcomings of earlier iterative algorithms. Our solution, ReconNet, is a deep neural network, whose parameters are learned end-to-end to map block-wise compressive measurements of the scene to the desired image blocks. Reconstruction of an image becomes a simple forward pass through the network and can be done in real-time. We show empirically that our algorithm yields reconstructions with higher PSNRs compared to iterative algorithms at low measurement rates and in presence of measurement noise. We also propose a variant of ReconNet which uses adversarial loss in order to further improve reconstruction quality. We discuss how adding a fully connected layer to the existing ReconNet architecture allows for jointly learning the measurement matrix and the reconstruction algorithm in a single network. Experiments on real data obtained from a block compressive imager show that our networks are robust to unseen sensor noise. Finally, through an experiment in object tracking, we show that even at very low measurement rates, reconstructions using our algorithm possess rich semantic content that can be used for high level inference. |
| Tasks | Compressive Sensing, Object Tracking |
| Published | 2017-08-15 |
| URL | http://arxiv.org/abs/1708.04669v2 |
| http://arxiv.org/pdf/1708.04669v2.pdf | |
| PWC | https://paperswithcode.com/paper/convolutional-neural-networks-for-non |
| Repo | |
| Framework | |
Algebraic Image Processing
| Title | Algebraic Image Processing |
| Authors | Enrico Celeghini |
| Abstract | We propose an approach to image processing related to algebraic operators acting in the space of images. In view of the interest in the applications in optics and computer science, mathematical aspects of the paper have been simplified as much as possible. Underlying theory, related to rigged Hilbert spaces and Lie algebras, is discussed elsewhere |
| Tasks | |
| Published | 2017-10-11 |
| URL | http://arxiv.org/abs/1710.04207v1 |
| http://arxiv.org/pdf/1710.04207v1.pdf | |
| PWC | https://paperswithcode.com/paper/algebraic-image-processing |
| Repo | |
| Framework | |
Convergence Analysis of Distributed Stochastic Gradient Descent with Shuffling
| Title | Convergence Analysis of Distributed Stochastic Gradient Descent with Shuffling |
| Authors | Qi Meng, Wei Chen, Yue Wang, Zhi-Ming Ma, Tie-Yan Liu |
| Abstract | When using stochastic gradient descent to solve large-scale machine learning problems, a common practice of data processing is to shuffle the training data, partition the data across multiple machines if needed, and then perform several epochs of training on the re-shuffled (either locally or globally) data. The above procedure makes the instances used to compute the gradients no longer independently sampled from the training data set. Then does the distributed SGD method have desirable convergence properties in this practical situation? In this paper, we give answers to this question. First, we give a mathematical formulation for the practical data processing procedure in distributed machine learning, which we call data partition with global/local shuffling. We observe that global shuffling is equivalent to without-replacement sampling if the shuffling operations are independent. We prove that SGD with global shuffling has convergence guarantee in both convex and non-convex cases. An interesting finding is that, the non-convex tasks like deep learning are more suitable to apply shuffling comparing to the convex tasks. Second, we conduct the convergence analysis for SGD with local shuffling. The convergence rate for local shuffling is slower than that for global shuffling, since it will lose some information if there’s no communication between partitioned data. Finally, we consider the situation when the permutation after shuffling is not uniformly distributed (insufficient shuffling), and discuss the condition under which this insufficiency will not influence the convergence rate. Our theoretical results provide important insights to large-scale machine learning, especially in the selection of data processing methods in order to achieve faster convergence and good speedup. Our theoretical findings are verified by extensive experiments on logistic regression and deep neural networks. |
| Tasks | |
| Published | 2017-09-29 |
| URL | http://arxiv.org/abs/1709.10432v1 |
| http://arxiv.org/pdf/1709.10432v1.pdf | |
| PWC | https://paperswithcode.com/paper/convergence-analysis-of-distributed |
| Repo | |
| Framework | |
Probabilistic Neural Network with Complex Exponential Activation Functions in Image Recognition using Deep Learning Framework
| Title | Probabilistic Neural Network with Complex Exponential Activation Functions in Image Recognition using Deep Learning Framework |
| Authors | Andrey Savchenko |
| Abstract | If the training dataset is not very large, image recognition is usually implemented with the transfer learning methods. In these methods the features are extracted using a deep convolutional neural network, which was preliminarily trained with an external very-large dataset. In this paper we consider the nonparametric classification of extracted feature vectors with the probabilistic neural network (PNN). The number of neurons at the pattern layer of the PNN is equal to the database size, which causes the low recognition performance and high memory space complexity of this network. We propose to overcome these drawbacks by replacing the exponential activation function in the Gaussian Parzen kernel to the complex exponential functions in the Fej'er kernel. We demonstrate that in this case it is possible to implement the network with the number of neurons in the pattern layer proportional to the cubic root of the database size. Thus, the proposed modification of the PNN makes it possible to significantly decrease runtime and memory complexities without loosing its main advantages, namely, extremely fast training procedure and the convergence to the optimal Bayesian decision. An experimental study in visual object category classification and unconstrained face recognition with contemporary deep neural networks have shown, that our approach obtains very efficient and rather accurate decisions for the small training sample in comparison with the well-known classifiers. |
| Tasks | Face Recognition, Transfer Learning |
| Published | 2017-08-09 |
| URL | http://arxiv.org/abs/1708.02733v1 |
| http://arxiv.org/pdf/1708.02733v1.pdf | |
| PWC | https://paperswithcode.com/paper/probabilistic-neural-network-with-complex |
| Repo | |
| Framework | |
Neural-based Natural Language Generation in Dialogue using RNN Encoder-Decoder with Semantic Aggregation
| Title | Neural-based Natural Language Generation in Dialogue using RNN Encoder-Decoder with Semantic Aggregation |
| Authors | Van-Khanh Tran, Le-Minh Nguyen |
| Abstract | Natural language generation (NLG) is an important component in spoken dialogue systems. This paper presents a model called Encoder-Aggregator-Decoder which is an extension of an Recurrent Neural Network based Encoder-Decoder architecture. The proposed Semantic Aggregator consists of two components: an Aligner and a Refiner. The Aligner is a conventional attention calculated over the encoded input information, while the Refiner is another attention or gating mechanism stacked over the attentive Aligner in order to further select and aggregate the semantic elements. The proposed model can be jointly trained both sentence planning and surface realization to produce natural language utterances. The model was extensively assessed on four different NLG domains, in which the experimental results showed that the proposed generator consistently outperforms the previous methods on all the NLG domains. |
| Tasks | Spoken Dialogue Systems, Text Generation |
| Published | 2017-06-21 |
| URL | http://arxiv.org/abs/1706.06714v3 |
| http://arxiv.org/pdf/1706.06714v3.pdf | |
| PWC | https://paperswithcode.com/paper/neural-based-natural-language-generation-in |
| Repo | |
| Framework | |
A Generative Model For Zero Shot Learning Using Conditional Variational Autoencoders
| Title | A Generative Model For Zero Shot Learning Using Conditional Variational Autoencoders |
| Authors | Ashish Mishra, M Shiva Krishna Reddy, Anurag Mittal, Hema A Murthy |
| Abstract | Zero shot learning in Image Classification refers to the setting where images from some novel classes are absent in the training data but other information such as natural language descriptions or attribute vectors of the classes are available. This setting is important in the real world since one may not be able to obtain images of all the possible classes at training. While previous approaches have tried to model the relationship between the class attribute space and the image space via some kind of a transfer function in order to model the image space correspondingly to an unseen class, we take a different approach and try to generate the samples from the given attributes, using a conditional variational autoencoder, and use the generated samples for classification of the unseen classes. By extensive testing on four benchmark datasets, we show that our model outperforms the state of the art, particularly in the more realistic generalized setting, where the training classes can also appear at the test time along with the novel classes. |
| Tasks | Image Classification, Zero-Shot Learning |
| Published | 2017-09-03 |
| URL | http://arxiv.org/abs/1709.00663v2 |
| http://arxiv.org/pdf/1709.00663v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-generative-model-for-zero-shot-learning |
| Repo | |
| Framework | |
Self-Similarity Based Time Warping
| Title | Self-Similarity Based Time Warping |
| Authors | Christopher J. Tralie |
| Abstract | In this work, we explore the problem of aligning two time-ordered point clouds which are spatially transformed and re-parameterized versions of each other. This has a diverse array of applications such as cross modal time series synchronization (e.g. MOCAP to video) and alignment of discretized curves in images. Most other works that address this problem attempt to jointly uncover a spatial alignment and correspondences between the two point clouds, or to derive local invariants to spatial transformations such as curvature before computing correspondences. By contrast, we sidestep spatial alignment completely by using self-similarity matrices (SSMs) as a proxy to the time-ordered point clouds, since self-similarity matrices are blind to isometries and respect global geometry. Our algorithm, dubbed “Isometry Blind Dynamic Time Warping” (IBDTW), is simple and general, and we show that its associated dissimilarity measure lower bounds the L1 Gromov-Hausdorff distance between the two point sets when restricted to warping paths. We also present a local, partial alignment extension of IBDTW based on the Smith Waterman algorithm. This eliminates the need for tedious manual cropping of time series, which is ordinarily necessary for global alignment algorithms to function properly. |
| Tasks | Time Series |
| Published | 2017-11-20 |
| URL | http://arxiv.org/abs/1711.07513v1 |
| http://arxiv.org/pdf/1711.07513v1.pdf | |
| PWC | https://paperswithcode.com/paper/self-similarity-based-time-warping |
| Repo | |
| Framework | |
Pragmatic-Pedagogic Value Alignment
| Title | Pragmatic-Pedagogic Value Alignment |
| Authors | Jaime F. Fisac, Monica A. Gates, Jessica B. Hamrick, Chang Liu, Dylan Hadfield-Menell, Malayandi Palaniappan, Dhruv Malik, S. Shankar Sastry, Thomas L. Griffiths, Anca D. Dragan |
| Abstract | As intelligent systems gain autonomy and capability, it becomes vital to ensure that their objectives match those of their human users; this is known as the value-alignment problem. In robotics, value alignment is key to the design of collaborative robots that can integrate into human workflows, successfully inferring and adapting to their users’ objectives as they go. We argue that a meaningful solution to value alignment must combine multi-agent decision theory with rich mathematical models of human cognition, enabling robots to tap into people’s natural collaborative capabilities. We present a solution to the cooperative inverse reinforcement learning (CIRL) dynamic game based on well-established cognitive models of decision making and theory of mind. The solution captures a key reciprocity relation: the human will not plan her actions in isolation, but rather reason pedagogically about how the robot might learn from them; the robot, in turn, can anticipate this and interpret the human’s actions pragmatically. To our knowledge, this work constitutes the first formal analysis of value alignment grounded in empirically validated cognitive models. |
| Tasks | Decision Making |
| Published | 2017-07-20 |
| URL | http://arxiv.org/abs/1707.06354v2 |
| http://arxiv.org/pdf/1707.06354v2.pdf | |
| PWC | https://paperswithcode.com/paper/pragmatic-pedagogic-value-alignment |
| Repo | |
| Framework | |
An Interpretable Knowledge Transfer Model for Knowledge Base Completion
| Title | An Interpretable Knowledge Transfer Model for Knowledge Base Completion |
| Authors | Qizhe Xie, Xuezhe Ma, Zihang Dai, Eduard Hovy |
| Abstract | Knowledge bases are important resources for a variety of natural language processing tasks but suffer from incompleteness. We propose a novel embedding model, \emph{ITransF}, to perform knowledge base completion. Equipped with a sparse attention mechanism, ITransF discovers hidden concepts of relations and transfer statistical strength through the sharing of concepts. Moreover, the learned associations between relations and concepts, which are represented by sparse attention vectors, can be interpreted easily. We evaluate ITransF on two benchmark datasets—WN18 and FB15k for knowledge base completion and obtains improvements on both the mean rank and Hits@10 metrics, over all baselines that do not use additional information. |
| Tasks | Knowledge Base Completion, Transfer Learning |
| Published | 2017-04-19 |
| URL | http://arxiv.org/abs/1704.05908v2 |
| http://arxiv.org/pdf/1704.05908v2.pdf | |
| PWC | https://paperswithcode.com/paper/an-interpretable-knowledge-transfer-model-for |
| Repo | |
| Framework | |
Systems, Actors and Agents: Operation in a multicomponent environment
| Title | Systems, Actors and Agents: Operation in a multicomponent environment |
| Authors | Mark Burgin |
| Abstract | Multi-agent approach has become popular in computer science and technology. However, the conventional models of multi-agent and multicomponent systems implicitly or explicitly assume existence of absolute time or even do not include time in the set of defining parameters. At the same time, it is proved theoretically and validated experimentally that there are different times and time scales in a variety of real systems - physical, chemical, biological, social, informational, etc. Thus, the goal of this work is construction of a multi-agent multicomponent system models with concurrency of processes and diversity of actions. To achieve this goal, a mathematical system actor model is elaborated and its properties are studied. |
| Tasks | |
| Published | 2017-11-16 |
| URL | http://arxiv.org/abs/1711.08319v1 |
| http://arxiv.org/pdf/1711.08319v1.pdf | |
| PWC | https://paperswithcode.com/paper/systems-actors-and-agents-operation-in-a |
| Repo | |
| Framework | |
The Complexity of Campaigning
| Title | The Complexity of Campaigning |
| Authors | Cory Siler, Luke Harold Miles, Judy Goldsmith |
| Abstract | In “The Logic of Campaigning”, Dean and Parikh consider a candidate making campaign statements to appeal to the voters. They model these statements as Boolean formulas over variables that represent stances on the issues, and study optimal candidate strategies under three proposed models of voter preferences based on the assignments that satisfy these formulas. We prove that voter utility evaluation is computationally hard under these preference models (in one case, #P-hard), along with certain problems related to candidate strategic reasoning. Our results raise questions about the desirable characteristics of a voter preference model and to what extent a polynomial-time-evaluable function can capture them. |
| Tasks | |
| Published | 2017-06-20 |
| URL | http://arxiv.org/abs/1706.06243v2 |
| http://arxiv.org/pdf/1706.06243v2.pdf | |
| PWC | https://paperswithcode.com/paper/the-complexity-of-campaigning |
| Repo | |
| Framework | |
A Contextual Bandit Approach for Stream-Based Active Learning
| Title | A Contextual Bandit Approach for Stream-Based Active Learning |
| Authors | Linqi Song, Jie Xu |
| Abstract | Contextual bandit algorithms – a class of multi-armed bandit algorithms that exploit the contextual information – have been shown to be effective in solving sequential decision making problems under uncertainty. A common assumption adopted in the literature is that the realized (ground truth) reward by taking the selected action is observed by the learner at no cost, which, however, is not realistic in many practical scenarios. When observing the ground truth reward is costly, a key challenge for the learner is how to judiciously acquire the ground truth by assessing the benefits and costs in order to balance learning efficiency and learning cost. From the information theoretic perspective, a perhaps even more interesting question is how much efficiency might be lost due to this cost. In this paper, we design a novel contextual bandit-based learning algorithm and endow it with the active learning capability. The key feature of our algorithm is that in addition to sending a query to an annotator for the ground truth, prior information about the ground truth learned by the learner is sent together, thereby reducing the query cost. We prove that by carefully choosing the algorithm parameters, the learning regret of the proposed algorithm achieves the same order as that of conventional contextual bandit algorithms in cost-free scenarios, implying that, surprisingly, cost due to acquiring the ground truth does not increase the learning regret in the long-run. Our analysis shows that prior information about the ground truth plays a critical role in improving the system performance in scenarios where active learning is necessary. |
| Tasks | Active Learning, Decision Making |
| Published | 2017-01-24 |
| URL | http://arxiv.org/abs/1701.06725v1 |
| http://arxiv.org/pdf/1701.06725v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-contextual-bandit-approach-for-stream-based |
| Repo | |
| Framework | |
