October 20, 2019

3279 words 16 mins read

Paper Group AWR 199

Multivariate LSTM-FCNs for Time Series Classification. FasTer: Fast Tensor Completion with Nonconvex Regularization. Disentangled Representation Learning for Non-Parallel Text Style Transfer. Expert identification of visual primitives used by CNNs during mammogram classification. Financial Trading as a Game: A Deep Reinforcement Learning Approach. …

Multivariate LSTM-FCNs for Time Series Classification


Title	Multivariate LSTM-FCNs for Time Series Classification
Authors	Fazle Karim, Somshubra Majumdar, Houshang Darabi, Samuel Harford
Abstract	Over the past decade, multivariate time series classification has received great attention. We propose transforming the existing univariate time series classification models, the Long Short Term Memory Fully Convolutional Network (LSTM-FCN) and Attention LSTM-FCN (ALSTM-FCN), into a multivariate time series classification model by augmenting the fully convolutional block with a squeeze-and-excitation block to further improve accuracy. Our proposed models outperform most state-of-the-art models while requiring minimum preprocessing. The proposed models work efficiently on various complex multivariate time series classification tasks such as activity recognition or action recognition. Furthermore, the proposed models are highly efficient at test time and small enough to deploy on memory constrained systems.
Tasks	Activity Recognition, Temporal Action Localization, Time Series, Time Series Classification
Published	2018-01-14
URL	https://arxiv.org/abs/1801.04503v2
PDF	https://arxiv.org/pdf/1801.04503v2.pdf
PWC	https://paperswithcode.com/paper/multivariate-lstm-fcns-for-time-series
Repo	https://github.com/NewKnowledge/TimeSeries-D3M-Wrappers
Framework	tf

FasTer: Fast Tensor Completion with Nonconvex Regularization


Title	FasTer: Fast Tensor Completion with Nonconvex Regularization
Authors	Quanming Yao, James T Kwok, Bo Han
Abstract	Low-rank tensor completion problem aims to recover a tensor from limited observations, which has many real-world applications. Due to the easy optimization, the convex overlapping nuclear norm has been popularly used for tensor completion. However, it over-penalizes top singular values and lead to biased estimations. In this paper, we propose to use the nonconvex regularizer, which can less penalize large singular values, instead of the convex one for tensor completion. However, as the new regularizer is nonconvex and overlapped with each other, existing algorithms are either too slow or suffer from the huge memory cost. To address these issues, we develop an efficient and scalable algorithm, which is based on the proximal average (PA) algorithm, for real-world problems. Compared with the direct usage of PA algorithm, the proposed algorithm runs orders faster and needs orders less space. We further speed up the proposed algorithm with the acceleration technique, and show the convergence to critical points is still guaranteed. Experimental comparisons of the proposed approach are made with various other tensor completion approaches. Empirical results show that the proposed algorithm is very fast and can produce much better recovery performance.
Tasks
Published	2018-07-23
URL	http://arxiv.org/abs/1807.08725v3
PDF	http://arxiv.org/pdf/1807.08725v3.pdf
PWC	https://paperswithcode.com/paper/faster-fast-tensor-completion-with-nonconvex
Repo	https://github.com/quanmingyao/FasTer
Framework	none

Disentangled Representation Learning for Non-Parallel Text Style Transfer


Title	Disentangled Representation Learning for Non-Parallel Text Style Transfer
Authors	Vineet John, Lili Mou, Hareesh Bahuleyan, Olga Vechtomova
Abstract	This paper tackles the problem of disentangling the latent variables of style and content in language models. We propose a simple yet effective approach, which incorporates auxiliary multi-task and adversarial objectives, for label prediction and bag-of-words prediction, respectively. We show, both qualitatively and quantitatively, that the style and content are indeed disentangled in the latent space. This disentangled latent representation learning method is applied to style transfer on non-parallel corpora. We achieve substantially better results in terms of transfer accuracy, content preservation and language fluency, in comparison to previous state-of-the-art approaches.
Tasks	Latent Variable Models, Representation Learning, Style Transfer, Text Style Transfer
Published	2018-08-13
URL	http://arxiv.org/abs/1808.04339v2
PDF	http://arxiv.org/pdf/1808.04339v2.pdf
PWC	https://paperswithcode.com/paper/disentangled-representation-learning-for-non
Repo	https://github.com/h3lio5/linguistic-style-transfer-pytorch
Framework	pytorch

Expert identification of visual primitives used by CNNs during mammogram classification


Title	Expert identification of visual primitives used by CNNs during mammogram classification
Authors	Jimmy Wu, Diondra Peck, Scott Hsieh, Vandana Dialani, Constance D. Lehman, Bolei Zhou, Vasilis Syrgkanis, Lester Mackey, Genevieve Patterson
Abstract	This work interprets the internal representations of deep neural networks trained for classification of diseased tissue in 2D mammograms. We propose an expert-in-the-loop interpretation method to label the behavior of internal units in convolutional neural networks (CNNs). Expert radiologists identify that the visual patterns detected by the units are correlated with meaningful medical phenomena such as mass tissue and calcificated vessels. We demonstrate that several trained CNN models are able to produce explanatory descriptions to support the final classification decisions. We view this as an important first step toward interpreting the internal representations of medical classification CNNs and explaining their predictions.
Tasks
Published	2018-03-13
URL	http://arxiv.org/abs/1803.04858v1
PDF	http://arxiv.org/pdf/1803.04858v1.pdf
PWC	https://paperswithcode.com/paper/expert-identification-of-visual-primitives
Repo	https://github.com/jimmyyhwu/ddsm-visual-primitives
Framework	pytorch

Financial Trading as a Game: A Deep Reinforcement Learning Approach


Title	Financial Trading as a Game: A Deep Reinforcement Learning Approach
Authors	Chien Yi Huang
Abstract	An automatic program that generates constant profit from the financial market is lucrative for every market practitioner. Recent advance in deep reinforcement learning provides a framework toward end-to-end training of such trading agent. In this paper, we propose an Markov Decision Process (MDP) model suitable for the financial trading task and solve it with the state-of-the-art deep recurrent Q-network (DRQN) algorithm. We propose several modifications to the existing learning algorithm to make it more suitable under the financial trading setting, namely 1. We employ a substantially small replay memory (only a few hundreds in size) compared to ones used in modern deep reinforcement learning algorithms (often millions in size.) 2. We develop an action augmentation technique to mitigate the need for random exploration by providing extra feedback signals for all actions to the agent. This enables us to use greedy policy over the course of learning and shows strong empirical performance compared to more commonly used epsilon-greedy exploration. However, this technique is specific to financial trading under a few market assumptions. 3. We sample a longer sequence for recurrent neural network training. A side product of this mechanism is that we can now train the agent for every T steps. This greatly reduces training time since the overall computation is down by a factor of T. We combine all of the above into a complete online learning algorithm and validate our approach on the spot foreign exchange market.
Tasks
Published	2018-07-08
URL	http://arxiv.org/abs/1807.02787v1
PDF	http://arxiv.org/pdf/1807.02787v1.pdf
PWC	https://paperswithcode.com/paper/financial-trading-as-a-game-a-deep
Repo	https://github.com/sachink2010/AutomatedStockTrading-DeepQ-Learning
Framework	none

Playing Atari with Six Neurons


Title	Playing Atari with Six Neurons
Authors	Giuseppe Cuccu, Julian Togelius, Philippe Cudre-Mauroux
Abstract	Deep reinforcement learning, applied to vision-based problems like Atari games, maps pixels directly to actions; internally, the deep neural network bears the responsibility of both extracting useful information and making decisions based on it. By separating the image processing from decision-making, one could better understand the complexity of each task, as well as potentially find smaller policy representations that are easier for humans to understand and may generalize better. To this end, we propose a new method for learning policies and compact state representations separately but simultaneously for policy approximation in reinforcement learning. State representations are generated by an encoder based on two novel algorithms: Increasing Dictionary Vector Quantization makes the encoder capable of growing its dictionary size over time, to address new observations as they appear in an open-ended online-learning context; Direct Residuals Sparse Coding encodes observations by disregarding reconstruction error minimization, and aiming instead for highest information inclusion. The encoder autonomously selects observations online to train on, in order to maximize code sparsity. As the dictionary size increases, the encoder produces increasingly larger inputs for the neural network: this is addressed by a variation of the Exponential Natural Evolution Strategies algorithm which adapts its probability distribution dimensionality along the run. We test our system on a selection of Atari games using tiny neural networks of only 6 to 18 neurons (depending on the game’s controls). These are still capable of achieving results comparable—and occasionally superior—to state-of-the-art techniques which use two orders of magnitude more neurons.
Tasks	Atari Games, Decision Making, Quantization
Published	2018-06-04
URL	http://arxiv.org/abs/1806.01363v2
PDF	http://arxiv.org/pdf/1806.01363v2.pdf
PWC	https://paperswithcode.com/paper/playing-atari-with-six-neurons
Repo	https://github.com/giuse/DNE
Framework	none

Monte Carlo Tree Search for Asymmetric Trees


Title	Monte Carlo Tree Search for Asymmetric Trees
Authors	Thomas M. Moerland, Joost Broekens, Aske Plaat, Catholijn M. Jonker
Abstract	We present an extension of Monte Carlo Tree Search (MCTS) that strongly increases its efficiency for trees with asymmetry and/or loops. Asymmetric termination of search trees introduces a type of uncertainty for which the standard upper confidence bound (UCB) formula does not account. Our first algorithm (MCTS-T), which assumes a non-stochastic environment, backs-up tree structure uncertainty and leverages it for exploration in a modified UCB formula. Results show vastly improved efficiency in a well-known asymmetric domain in which MCTS performs arbitrarily bad. Next, we connect the ideas about asymmetric termination to the presence of loops in the tree, where the same state appears multiple times in a single trace. An extension to our algorithm (MCTS-T+), which in addition to non-stochasticity assumes full state observability, further increases search efficiency for domains with loops as well. Benchmark testing on a set of OpenAI Gym and Atari 2600 games indicates that our algorithms always perform better than or at least equivalent to standard MCTS, and could be first-choice tree search algorithms for non-stochastic, fully-observable environments.
Tasks	Atari Games
Published	2018-05-23
URL	http://arxiv.org/abs/1805.09218v1
PDF	http://arxiv.org/pdf/1805.09218v1.pdf
PWC	https://paperswithcode.com/paper/monte-carlo-tree-search-for-asymmetric-trees
Repo	https://github.com/jeapostrophe/monaco
Framework	none

BindsNET: A machine learning-oriented spiking neural networks library in Python


Title	BindsNET: A machine learning-oriented spiking neural networks library in Python
Authors	Hananel Hazan, Daniel J. Saunders, Hassaan Khan, Darpan T. Sanghavi, Hava T. Siegelmann, Robert Kozma
Abstract	The development of spiking neural network simulation software is a critical component enabling the modeling of neural systems and the development of biologically inspired algorithms. Existing software frameworks support a wide range of neural functionality, software abstraction levels, and hardware devices, yet are typically not suitable for rapid prototyping or application to problems in the domain of machine learning. In this paper, we describe a new Python package for the simulation of spiking neural networks, specifically geared towards machine learning and reinforcement learning. Our software, called BindsNET, enables rapid building and simulation of spiking networks and features user-friendly, concise syntax. BindsNET is built on top of the PyTorch deep neural networks library, enabling fast CPU and GPU computation for large spiking networks. The BindsNET framework can be adjusted to meet the needs of other existing computing and hardware environments, e.g., TensorFlow. We also provide an interface into the OpenAI gym library, allowing for training and evaluation of spiking networks on reinforcement learning problems. We argue that this package facilitates the use of spiking networks for large-scale machine learning experimentation, and show some simple examples of how we envision BindsNET can be used in practice. BindsNET code is available at https://github.com/Hananel-Hazan/bindsnet
Tasks
Published	2018-06-04
URL	http://arxiv.org/abs/1806.01423v2
PDF	http://arxiv.org/pdf/1806.01423v2.pdf
PWC	https://paperswithcode.com/paper/bindsnet-a-machine-learning-oriented-spiking
Repo	https://github.com/Hananel-Hazan/bindsnet
Framework	pytorch

Fractal AI: A fragile theory of intelligence


Title	Fractal AI: A fragile theory of intelligence
Authors	Sergio Hernandez Cerezo, Guillem Duran Ballester
Abstract	Fractal AI is a theory for general artificial intelligence. It allows deriving new mathematical tools that constitute the foundations for a new kind of stochastic calculus, by modelling information using cellular automaton-like structures instead of smooth functions. In the repository included we are presenting a new Agent, derived from the first principles of the theory, which is capable of solving Atari games several orders of magnitude more efficiently than other similar techniques, like Monte Carlo Tree Search. The code provided shows how it is now possible to beat some of the current State of The Art benchmarks on Atari games, without previous learning and using less than 1000 samples to calculate each one of the actions when standard MCTS uses 3 Million samples. Among other things, Fractal AI makes it possible to generate a huge database of top performing examples with a very little amount of computation required, transforming Reinforcement Learning into a supervised problem. The algorithm presented is capable of solving the exploration vs exploitation dilemma on both the discrete and continuous cases, while maintaining control over any aspect of the behaviour of the Agent. From a general approach, new techniques presented here have direct applications to other areas such as Non-equilibrium thermodynamics, chemistry, quantum physics, economics, information theory, and non-linear control theory.
Tasks	Atari Games
Published	2018-03-13
URL	https://arxiv.org/abs/1803.05049v4
PDF	https://arxiv.org/pdf/1803.05049v4.pdf
PWC	https://paperswithcode.com/paper/fractal-ai-a-fragile-theory-of-intelligence
Repo	https://github.com/Guillemdb/fragile
Framework	none

Accelerated Methods for Deep Reinforcement Learning


Title	Accelerated Methods for Deep Reinforcement Learning
Authors	Adam Stooke, Pieter Abbeel
Abstract	Deep reinforcement learning (RL) has achieved many recent successes, yet experiment turn-around time remains a key bottleneck in research and in practice. We investigate how to optimize existing deep RL algorithms for modern computers, specifically for a combination of CPUs and GPUs. We confirm that both policy gradient and Q-value learning algorithms can be adapted to learn using many parallel simulator instances. We further find it possible to train using batch sizes considerably larger than are standard, without negatively affecting sample complexity or final performance. We leverage these facts to build a unified framework for parallelization that dramatically hastens experiments in both classes of algorithm. All neural network computations use GPUs, accelerating both data collection and training. Our results include using an entire DGX-1 to learn successful strategies in Atari games in mere minutes, using both synchronous and asynchronous algorithms.
Tasks	Atari Games
Published	2018-03-07
URL	http://arxiv.org/abs/1803.02811v2
PDF	http://arxiv.org/pdf/1803.02811v2.pdf
PWC	https://paperswithcode.com/paper/accelerated-methods-for-deep-reinforcement
Repo	https://github.com/astooke/accel_rl
Framework	none

A Framework for Evaluating 6-DOF Object Trackers


Title	A Framework for Evaluating 6-DOF Object Trackers
Authors	Mathieu Garon, Denis Laurendeau, Jean-François Lalonde
Abstract	We present a challenging and realistic novel dataset for evaluating 6-DOF object tracking algorithms. Existing datasets show serious limitations—notably, unrealistic synthetic data, or real data with large fiducial markers—preventing the community from obtaining an accurate picture of the state-of-the-art. Using a data acquisition pipeline based on a commercial motion capture system for acquiring accurate ground truth poses of real objects with respect to a Kinect V2 camera, we build a dataset which contains a total of 297 calibrated sequences. They are acquired in three different scenarios to evaluate the performance of trackers: stability, robustness to occlusion and accuracy during challenging interactions between a person and the object. We conduct an extensive study of a deep 6-DOF tracking architecture and determine a set of optimal parameters. We enhance the architecture and the training methodology to train a 6-DOF tracker that can robustly generalize to objects never seen during training, and demonstrate favorable performance compared to previous approaches trained specifically on the objects to track.
Tasks	Motion Capture, Object Tracking
Published	2018-03-27
URL	http://arxiv.org/abs/1803.10075v3
PDF	http://arxiv.org/pdf/1803.10075v3.pdf
PWC	https://paperswithcode.com/paper/a-framework-for-evaluating-6-dof-object
Repo	https://github.com/lvsn/6DOF_tracking_evaluation
Framework	none

SLAYER: Spike Layer Error Reassignment in Time


Title	SLAYER: Spike Layer Error Reassignment in Time
Authors	Sumit Bam Shrestha, Garrick Orchard
Abstract	Configuring deep Spiking Neural Networks (SNNs) is an exciting research avenue for low power spike event based computation. However, the spike generation function is non-differentiable and therefore not directly compatible with the standard error backpropagation algorithm. In this paper, we introduce a new general backpropagation mechanism for learning synaptic weights and axonal delays which overcomes the problem of non-differentiability of the spike function and uses a temporal credit assignment policy for backpropagating error to preceding layers. We describe and release a GPU accelerated software implementation of our method which allows training both fully connected and convolutional neural network (CNN) architectures. Using our software, we compare our method against existing SNN based learning approaches and standard ANN to SNN conversion techniques and show that our method achieves state of the art performance for an SNN on the MNIST, NMNIST, DVS Gesture, and TIDIGITS datasets.
Tasks
Published	2018-09-05
URL	http://arxiv.org/abs/1810.08646v1
PDF	http://arxiv.org/pdf/1810.08646v1.pdf
PWC	https://paperswithcode.com/paper/slayer-spike-layer-error-reassignment-in-time
Repo	https://github.com/bamsumit/slayerPytorch
Framework	pytorch

Joint Enhancement and Denoising Method via Sequential Decomposition


Title	Joint Enhancement and Denoising Method via Sequential Decomposition
Authors	Xutong Ren, Mading Li, Wen-Huang Cheng, Jiaying Liu
Abstract	Many low-light enhancement methods ignore intensive noise in original images. As a result, they often simultaneously enhance the noise as well. Furthermore, extra denoising procedures adopted by most methods ruin the details. In this paper, we introduce a joint low-light enhancement and denoising strategy, aimed at obtaining well-enhanced low-light images while getting rid of the inherent noise issue simultaneously. The proposed method performs Retinex model based decomposition in a successive sequence, which sequentially estimates a piece-wise smoothed illumination and a noise-suppressed reflectance. After getting the illumination and reflectance map, we adjust the illumination layer and generate our enhancement result. In this noise-suppressed sequential decomposition process we enforce the spatial smoothness on each component and skillfully make use of weight matrices to suppress the noise and improve the contrast. Results of extensive experiments demonstrate the effectiveness and practicability of our method. It performs well for a wide variety of images, and achieves better or comparable quality compared with the state-of-the-art methods.
Tasks	Denoising
Published	2018-04-23
URL	http://arxiv.org/abs/1804.08468v3
PDF	http://arxiv.org/pdf/1804.08468v3.pdf
PWC	https://paperswithcode.com/paper/joint-enhancement-and-denoising-method-via
Repo	https://github.com/tonghelen/JED-Method
Framework	none

Variational Autoencoder with Implicit Optimal Priors


Title	Variational Autoencoder with Implicit Optimal Priors
Authors	Hiroshi Takahashi, Tomoharu Iwata, Yuki Yamanaka, Masanori Yamada, Satoshi Yagi
Abstract	The variational autoencoder (VAE) is a powerful generative model that can estimate the probability of a data point by using latent variables. In the VAE, the posterior of the latent variable given the data point is regularized by the prior of the latent variable using Kullback Leibler (KL) divergence. Although the standard Gaussian distribution is usually used for the prior, this simple prior incurs over-regularization. As a sophisticated prior, the aggregated posterior has been introduced, which is the expectation of the posterior over the data distribution. This prior is optimal for the VAE in terms of maximizing the training objective function. However, KL divergence with the aggregated posterior cannot be calculated in a closed form, which prevents us from using this optimal prior. With the proposed method, we introduce the density ratio trick to estimate this KL divergence without modeling the aggregated posterior explicitly. Since the density ratio trick does not work well in high dimensions, we rewrite this KL divergence that contains the high-dimensional density ratio into the sum of the analytically calculable term and the low-dimensional density ratio term, to which the density ratio trick is applied. Experiments on various datasets show that the VAE with this implicit optimal prior achieves high density estimation performance.
Tasks	Density Estimation
Published	2018-09-14
URL	https://arxiv.org/abs/1809.05284v2
PDF	https://arxiv.org/pdf/1809.05284v2.pdf
PWC	https://paperswithcode.com/paper/variational-autoencoder-with-implicit-optimal
Repo	https://github.com/takahashihiroshi/vae_iop
Framework	pytorch

Deep RNN Framework for Visual Sequential Applications


Title	Deep RNN Framework for Visual Sequential Applications
Authors	Bo Pang, Kaiwen Zha, Hanwen Cao, Chen Shi, Cewu Lu
Abstract	Extracting temporal and representation features efficiently plays a pivotal role in understanding visual sequence information. To deal with this, we propose a new recurrent neural framework that can be stacked deep effectively. There are mainly two novel designs in our deep RNN framework: one is a new RNN module called Context Bridge Module (CBM) which splits the information flowing along the sequence (temporal direction) and along depth (spatial representation direction), making it easier to train when building deep by balancing these two directions; the other is the Overlap Coherence Training Scheme that reduces the training complexity for long visual sequential tasks on account of the limitation of computing resources. We provide empirical evidence to show that our deep RNN framework is easy to optimize and can gain accuracy from the increased depth on several visual sequence problems. On these tasks, we evaluate our deep RNN framework with 15 layers, 7* than conventional RNN networks, but it is still easy to train. Our deep framework achieves more than 11% relative improvements over shallow RNN models on Kinetics, UCF-101, and HMDB-51 for video classification. For auxiliary annotation, after replacing the shallow RNN part of Polygon-RNN with our 15-layer deep CBM, the performance improves by 14.7%. For video future prediction, our deep RNN improves the state-of-the-art shallow model’s performance by 2.4% on PSNR and SSIM. The code and trained models are published accompanied by this paper: https://github.com/BoPang1996/Deep-RNN-Framework.
Tasks	Future prediction, Video Classification
Published	2018-11-25
URL	https://arxiv.org/abs/1811.09961v4
PDF	https://arxiv.org/pdf/1811.09961v4.pdf
PWC	https://paperswithcode.com/paper/deep-rnn-framework-for-visual-sequential
Repo	https://github.com/BoPang1996/Deep-RNN-Framework
Framework	pytorch