Paper Group ANR 157
Sequential Recurrent Neural Networks for Language Modeling. Learning Unknown Markov Decision Processes: A Thompson Sampling Approach. Bicycle Detection Based On Multi-feature and Multi-frame Fusion in low-resolution traffic videos. When Waiting is not an Option : Learning Options with a Deliberation Cost. Transfer of View-manifold Learning to Simil …
Sequential Recurrent Neural Networks for Language Modeling
| Title | Sequential Recurrent Neural Networks for Language Modeling |
| Authors | Youssef Oualil, Clayton Greenberg, Mittul Singh, Dietrich Klakow |
| Abstract | Feedforward Neural Network (FNN)-based language models estimate the probability of the next word based on the history of the last N words, whereas Recurrent Neural Networks (RNN) perform the same task based only on the last word and some context information that cycles in the network. This paper presents a novel approach, which bridges the gap between these two categories of networks. In particular, we propose an architecture which takes advantage of the explicit, sequential enumeration of the word history in FNN structure while enhancing each word representation at the projection layer through recurrent context information that evolves in the network. The context integration is performed using an additional word-dependent weight matrix that is also learned during the training. Extensive experiments conducted on the Penn Treebank (PTB) and the Large Text Compression Benchmark (LTCB) corpus showed a significant reduction of the perplexity when compared to state-of-the-art feedforward as well as recurrent neural network architectures. |
| Tasks | Language Modelling |
| Published | 2017-03-23 |
| URL | http://arxiv.org/abs/1703.08068v1 |
| http://arxiv.org/pdf/1703.08068v1.pdf | |
| PWC | https://paperswithcode.com/paper/sequential-recurrent-neural-networks-for |
| Repo | |
| Framework | |
Learning Unknown Markov Decision Processes: A Thompson Sampling Approach
| Title | Learning Unknown Markov Decision Processes: A Thompson Sampling Approach |
| Authors | Yi Ouyang, Mukul Gagrani, Ashutosh Nayyar, Rahul Jain |
| Abstract | We consider the problem of learning an unknown Markov Decision Process (MDP) that is weakly communicating in the infinite horizon setting. We propose a Thompson Sampling-based reinforcement learning algorithm with dynamic episodes (TSDE). At the beginning of each episode, the algorithm generates a sample from the posterior distribution over the unknown model parameters. It then follows the optimal stationary policy for the sampled model for the rest of the episode. The duration of each episode is dynamically determined by two stopping criteria. The first stopping criterion controls the growth rate of episode length. The second stopping criterion happens when the number of visits to any state-action pair is doubled. We establish $\tilde O(HS\sqrt{AT})$ bounds on expected regret under a Bayesian setting, where $S$ and $A$ are the sizes of the state and action spaces, $T$ is time, and $H$ is the bound of the span. This regret bound matches the best available bound for weakly communicating MDPs. Numerical results show it to perform better than existing algorithms for infinite horizon MDPs. |
| Tasks | |
| Published | 2017-09-14 |
| URL | http://arxiv.org/abs/1709.04570v1 |
| http://arxiv.org/pdf/1709.04570v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-unknown-markov-decision-processes-a |
| Repo | |
| Framework | |
Bicycle Detection Based On Multi-feature and Multi-frame Fusion in low-resolution traffic videos
| Title | Bicycle Detection Based On Multi-feature and Multi-frame Fusion in low-resolution traffic videos |
| Authors | Yicheng Zhang, Qiang Ling |
| Abstract | As a major type of transportation equipments, bicycles, including electrical bicycles, are distributed almost everywhere in China. The accidents caused by bicycles have become a serious threat to the public safety. So bicycle detection is one major task of traffic video surveillance systems in China. In this paper, a method based on multi-feature and multi-frame fusion is presented for bicycle detection in low-resolution traffic videos. It first extracts some geometric features of objects from each frame image, then concatenate multiple features into a feature vector and use linear support vector machine (SVM) to learn a classifier, or put these features into a cascade classifier, to yield a preliminary detection result regarding whether an object is a bicycle. It further fuses these preliminary detection results from multiple frames to provide a more reliable detection decision, together with a confidence level of that decision. Experimental results show that this method based on multi-feature and multi-frame fusion can identify bicycles with high accuracy and low computational complexity. It is, therefore, applicable for real-time traffic video surveillance systems. |
| Tasks | |
| Published | 2017-06-11 |
| URL | http://arxiv.org/abs/1706.03309v1 |
| http://arxiv.org/pdf/1706.03309v1.pdf | |
| PWC | https://paperswithcode.com/paper/bicycle-detection-based-on-multi-feature-and |
| Repo | |
| Framework | |
When Waiting is not an Option : Learning Options with a Deliberation Cost
| Title | When Waiting is not an Option : Learning Options with a Deliberation Cost |
| Authors | Jean Harb, Pierre-Luc Bacon, Martin Klissarov, Doina Precup |
| Abstract | Recent work has shown that temporally extended actions (options) can be learned fully end-to-end as opposed to being specified in advance. While the problem of “how” to learn options is increasingly well understood, the question of “what” good options should be has remained elusive. We formulate our answer to what “good” options should be in the bounded rationality framework (Simon, 1957) through the notion of deliberation cost. We then derive practical gradient-based learning algorithms to implement this objective. Our results in the Arcade Learning Environment (ALE) show increased performance and interpretability. |
| Tasks | Atari Games |
| Published | 2017-09-14 |
| URL | http://arxiv.org/abs/1709.04571v1 |
| http://arxiv.org/pdf/1709.04571v1.pdf | |
| PWC | https://paperswithcode.com/paper/when-waiting-is-not-an-option-learning |
| Repo | |
| Framework | |
Transfer of View-manifold Learning to Similarity Perception of Novel Objects
| Title | Transfer of View-manifold Learning to Similarity Perception of Novel Objects |
| Authors | Xingyu Lin, Hao Wang, Zhihao Li, Yimeng Zhang, Alan Yuille, Tai Sing Lee |
| Abstract | We develop a model of perceptual similarity judgment based on re-training a deep convolution neural network (DCNN) that learns to associate different views of each 3D object to capture the notion of object persistence and continuity in our visual experience. The re-training process effectively performs distance metric learning under the object persistency constraints, to modify the view-manifold of object representations. It reduces the effective distance between the representations of different views of the same object without compromising the distance between those of the views of different objects, resulting in the untangling of the view-manifolds between individual objects within the same category and across categories. This untangling enables the model to discriminate and recognize objects within the same category, independent of viewpoints. We found that this ability is not limited to the trained objects, but transfers to novel objects in both trained and untrained categories, as well as to a variety of completely novel artificial synthetic objects. This transfer in learning suggests the modification of distance metrics in view- manifolds is more general and abstract, likely at the levels of parts, and independent of the specific objects or categories experienced during training. Interestingly, the resulting transformation of feature representation in the deep networks is found to significantly better match human perceptual similarity judgment than AlexNet, suggesting that object persistence could be an important constraint in the development of perceptual similarity judgment in biological neural networks. |
| Tasks | Metric Learning |
| Published | 2017-03-31 |
| URL | http://arxiv.org/abs/1704.00033v1 |
| http://arxiv.org/pdf/1704.00033v1.pdf | |
| PWC | https://paperswithcode.com/paper/transfer-of-view-manifold-learning-to |
| Repo | |
| Framework | |
Unwritten Languages Demand Attention Too! Word Discovery with Encoder-Decoder Models
| Title | Unwritten Languages Demand Attention Too! Word Discovery with Encoder-Decoder Models |
| Authors | Marcely Zanon Boito, Alexandre Berard, Aline Villavicencio, Laurent Besacier |
| Abstract | Word discovery is the task of extracting words from unsegmented text. In this paper we examine to what extent neural networks can be applied to this task in a realistic unwritten language scenario, where only small corpora and limited annotations are available. We investigate two scenarios: one with no supervision and another with limited supervision with access to the most frequent words. Obtained results show that it is possible to retrieve at least 27% of the gold standard vocabulary by training an encoder-decoder neural machine translation system with only 5,157 sentences. This result is close to those obtained with a task-specific Bayesian nonparametric model. Moreover, our approach has the advantage of generating translation alignments, which could be used to create a bilingual lexicon. As a future perspective, this approach is also well suited to work directly from speech. |
| Tasks | Machine Translation |
| Published | 2017-09-17 |
| URL | http://arxiv.org/abs/1709.05631v2 |
| http://arxiv.org/pdf/1709.05631v2.pdf | |
| PWC | https://paperswithcode.com/paper/unwritten-languages-demand-attention-too-word |
| Repo | |
| Framework | |
Large Neural Network Based Detection of Apnea, Bradycardia and Desaturation Events
| Title | Large Neural Network Based Detection of Apnea, Bradycardia and Desaturation Events |
| Authors | Antoine Honoré, Veronica Siljehav, Saikat Chatterjee, Eric Herlenius |
| Abstract | Apnea, bradycardia and desaturation (ABD) events often precede life-threatening events including sepsis in newborn babies. Here, we explore machine learning for detection of ABD events as a binary classification problem. We investigate the use of a large neural network to achieve a good detection performance. To be user friendly, the chosen neural network does not require a high level of parameter tuning. Furthermore, a limited amount of training data is available and the training dataset is unbalanced. Comparing with two widely used state-of-the-art machine learning algorithms, the large neural network is found to be efficient. Even with a limited and unbalanced training data, the large neural network provides a detection performance level that is feasible to use in clinical care. |
| Tasks | |
| Published | 2017-11-17 |
| URL | http://arxiv.org/abs/1711.06484v1 |
| http://arxiv.org/pdf/1711.06484v1.pdf | |
| PWC | https://paperswithcode.com/paper/large-neural-network-based-detection-of-apnea |
| Repo | |
| Framework | |
Autonomous Extracting a Hierarchical Structure of Tasks in Reinforcement Learning and Multi-task Reinforcement Learning
| Title | Autonomous Extracting a Hierarchical Structure of Tasks in Reinforcement Learning and Multi-task Reinforcement Learning |
| Authors | Behzad Ghazanfari, Matthew E. Taylor |
| Abstract | Reinforcement learning (RL), while often powerful, can suffer from slow learning speeds, particularly in high dimensional spaces. The autonomous decomposition of tasks and use of hierarchical methods hold the potential to significantly speed up learning in such domains. This paper proposes a novel practical method that can autonomously decompose tasks, by leveraging association rule mining, which discovers hidden relationship among entities in data mining. We introduce a novel method called ARM-HSTRL (Association Rule Mining to extract Hierarchical Structure of Tasks in Reinforcement Learning). It extracts temporal and structural relationships of sub-goals in RL, and multi-task RL. In particular,it finds sub-goals and relationship among them. It is shown the significant efficiency and performance of the proposed method in two main topics of RL. |
| Tasks | |
| Published | 2017-09-14 |
| URL | http://arxiv.org/abs/1709.04579v2 |
| http://arxiv.org/pdf/1709.04579v2.pdf | |
| PWC | https://paperswithcode.com/paper/autonomous-extracting-a-hierarchical |
| Repo | |
| Framework | |
Acceleration of Histogram-Based Contrast Enhancement via Selective Downsampling
| Title | Acceleration of Histogram-Based Contrast Enhancement via Selective Downsampling |
| Authors | Gang Cao, Huawei Tian, Lifang Yu, Xianglin Huang, Yongbin Wang |
| Abstract | In this paper, we propose a general framework to accelerate the universal histogram-based image contrast enhancement (CE) algorithms. Both spatial and gray-level selective down- sampling of digital images are adopted to decrease computational cost, while the visual quality of enhanced images is still preserved and without apparent degradation. Mapping function calibration is novelly proposed to reconstruct the pixel mapping on the gray levels missed by downsampling. As two case studies, accelerations of histogram equalization (HE) and the state-of-the-art global CE algorithm, i.e., spatial mutual information and PageRank (SMIRANK), are presented detailedly. Both quantitative and qualitative assessment results have verified the effectiveness of our proposed CE acceleration framework. In typical tests, computational efficiencies of HE and SMIRANK have been speeded up by about 3.9 and 13.5 times, respectively. |
| Tasks | Calibration |
| Published | 2017-09-14 |
| URL | http://arxiv.org/abs/1709.04583v2 |
| http://arxiv.org/pdf/1709.04583v2.pdf | |
| PWC | https://paperswithcode.com/paper/acceleration-of-histogram-based-contrast |
| Repo | |
| Framework | |
Multiclass MinMax Rank Aggregation
| Title | Multiclass MinMax Rank Aggregation |
| Authors | Pan Li, Olgica Milenkovic |
| Abstract | We introduce a new family of minmax rank aggregation problems under two distance measures, the Kendall {\tau} and the Spearman footrule. As the problems are NP-hard, we proceed to describe a number of constant-approximation algorithms for solving them. We conclude with illustrative applications of the aggregation methods on the Mallows model and genomic data. |
| Tasks | |
| Published | 2017-01-28 |
| URL | http://arxiv.org/abs/1701.08305v1 |
| http://arxiv.org/pdf/1701.08305v1.pdf | |
| PWC | https://paperswithcode.com/paper/multiclass-minmax-rank-aggregation |
| Repo | |
| Framework | |
Minimal Effort Back Propagation for Convolutional Neural Networks
| Title | Minimal Effort Back Propagation for Convolutional Neural Networks |
| Authors | Bingzhen Wei, Xu Sun, Xuancheng Ren, Jingjing Xu |
| Abstract | As traditional neural network consumes a significant amount of computing resources during back propagation, \citet{Sun2017mePropSB} propose a simple yet effective technique to alleviate this problem. In this technique, only a small subset of the full gradients are computed to update the model parameters. In this paper we extend this technique into the Convolutional Neural Network(CNN) to reduce calculation in back propagation, and the surprising results verify its validity in CNN: only 5% of the gradients are passed back but the model still achieves the same effect as the traditional CNN, or even better. We also show that the top-$k$ selection of gradients leads to a sparse calculation in back propagation, which may bring significant computational benefits for high computational complexity of convolution operation in CNN. |
| Tasks | |
| Published | 2017-09-18 |
| URL | http://arxiv.org/abs/1709.05804v1 |
| http://arxiv.org/pdf/1709.05804v1.pdf | |
| PWC | https://paperswithcode.com/paper/minimal-effort-back-propagation-for |
| Repo | |
| Framework | |
Methods for finding leader–follower equilibria with multiple followers
| Title | Methods for finding leader–follower equilibria with multiple followers |
| Authors | Nicola Basilico, Stefano Coniglio, Nicola Gatti |
| Abstract | The concept of leader–follower (or Stackelberg) equilibrium plays a central role in a number of real–world applications of game theory. While the case with a single follower has been thoroughly investigated, results with multiple followers are only sporadic and the problem of designing and evaluating computationally tractable equilibrium-finding algorithms is still largely open. In this work, we focus on the fundamental case where multiple followers play a Nash equilibrium once the leader has committed to a strategy—as we illustrate, the corresponding equilibrium finding problem can be easily shown to be $\mathcal{FNP}$–hard and not in Poly–$\mathcal{APX}$ unless $\mathcal{P} = \mathcal{NP}$ and therefore it is one among the hardest problems to solve and approximate. We propose nonconvex mathematical programming formulations and global optimization methods to find both exact and approximate equilibria, as well as a heuristic black box algorithm. All the methods and formulations that we introduce are thoroughly evaluated computationally. |
| Tasks | |
| Published | 2017-07-07 |
| URL | http://arxiv.org/abs/1707.02174v1 |
| http://arxiv.org/pdf/1707.02174v1.pdf | |
| PWC | https://paperswithcode.com/paper/methods-for-finding-leader-follower |
| Repo | |
| Framework | |
Sparse Quadratic Logistic Regression in Sub-quadratic Time
| Title | Sparse Quadratic Logistic Regression in Sub-quadratic Time |
| Authors | Karthikeyan Shanmugam, Murat Kocaoglu, Alexandros G. Dimakis, Sujay Sanghavi |
| Abstract | We consider support recovery in the quadratic logistic regression setting - where the target depends on both p linear terms $x_i$ and up to $p^2$ quadratic terms $x_i x_j$. Quadratic terms enable prediction/modeling of higher-order effects between features and the target, but when incorporated naively may involve solving a very large regression problem. We consider the sparse case, where at most $s$ terms (linear or quadratic) are non-zero, and provide a new faster algorithm. It involves (a) identifying the weak support (i.e. all relevant variables) and (b) standard logistic regression optimization only on these chosen variables. The first step relies on a novel insight about correlation tests in the presence of non-linearity, and takes $O(pn)$ time for $n$ samples - giving potentially huge computational gains over the naive approach. Motivated by insights from the boolean case, we propose a non-linear correlation test for non-binary finite support case that involves hashing a variable and then correlating with the output variable. We also provide experimental results to demonstrate the effectiveness of our methods. |
| Tasks | |
| Published | 2017-03-08 |
| URL | http://arxiv.org/abs/1703.02682v1 |
| http://arxiv.org/pdf/1703.02682v1.pdf | |
| PWC | https://paperswithcode.com/paper/sparse-quadratic-logistic-regression-in-sub |
| Repo | |
| Framework | |
DropoutDAgger: A Bayesian Approach to Safe Imitation Learning
| Title | DropoutDAgger: A Bayesian Approach to Safe Imitation Learning |
| Authors | Kunal Menda, Katherine Driggs-Campbell, Mykel J. Kochenderfer |
| Abstract | While imitation learning is becoming common practice in robotics, this approach often suffers from data mismatch and compounding errors. DAgger is an iterative algorithm that addresses these issues by continually aggregating training data from both the expert and novice policies, but does not consider the impact of safety. We present a probabilistic extension to DAgger, which uses the distribution over actions provided by the novice policy, for a given observation. Our method, which we call DropoutDAgger, uses dropout to train the novice as a Bayesian neural network that provides insight to its confidence. Using the distribution over the novice’s actions, we estimate a probabilistic measure of safety with respect to the expert action, tuned to balance exploration and exploitation. The utility of this approach is evaluated on the MuJoCo HalfCheetah and in a simple driving experiment, demonstrating improved performance and safety compared to other DAgger variants and classic imitation learning. |
| Tasks | Imitation Learning |
| Published | 2017-09-18 |
| URL | http://arxiv.org/abs/1709.06166v1 |
| http://arxiv.org/pdf/1709.06166v1.pdf | |
| PWC | https://paperswithcode.com/paper/dropoutdagger-a-bayesian-approach-to-safe |
| Repo | |
| Framework | |
Net2Vec: Deep Learning for the Network
| Title | Net2Vec: Deep Learning for the Network |
| Authors | Roberto Gonzalez, Filipe Manco, Alberto Garcia-Duran, Jose Mendes, Felipe Huici, Saverio Niccolini, Mathias Niepert |
| Abstract | We present Net2Vec, a flexible high-performance platform that allows the execution of deep learning algorithms in the communication network. Net2Vec is able to capture data from the network at more than 60Gbps, transform it into meaningful tuples and apply predictions over the tuples in real time. This platform can be used for different purposes ranging from traffic classification to network performance analysis. Finally, we showcase the use of Net2Vec by implementing and testing a solution able to profile network users at line rate using traces coming from a real network. We show that the use of deep learning for this case outperforms the baseline method both in terms of accuracy and performance. |
| Tasks | |
| Published | 2017-05-10 |
| URL | http://arxiv.org/abs/1705.03881v1 |
| http://arxiv.org/pdf/1705.03881v1.pdf | |
| PWC | https://paperswithcode.com/paper/net2vec-deep-learning-for-the-network |
| Repo | |
| Framework | |
