Paper Group ANR 366
Stock Chart Pattern recognition with Deep Learning. Sleep Arousal Detection from Polysomnography using the Scattering Transform and Recurrent Neural Networks. Learning to Search via Retrospective Imitation. Comparing CNN and LSTM character-level embeddings in BiLSTM-CRF models for chemical and disease named entity recognition. Measurement-based ada …
Stock Chart Pattern recognition with Deep Learning
Title | Stock Chart Pattern recognition with Deep Learning |
Authors | Marc Velay, Fabrice Daniel |
Abstract | This study evaluates the performances of CNN and LSTM for recognizing common charts patterns in a stock historical data. It presents two common patterns, the method used to build the training set, the neural networks architectures and the accuracies obtained. |
Tasks | |
Published | 2018-08-01 |
URL | http://arxiv.org/abs/1808.00418v1 |
http://arxiv.org/pdf/1808.00418v1.pdf | |
PWC | https://paperswithcode.com/paper/stock-chart-pattern-recognition-with-deep |
Repo | |
Framework | |
Sleep Arousal Detection from Polysomnography using the Scattering Transform and Recurrent Neural Networks
Title | Sleep Arousal Detection from Polysomnography using the Scattering Transform and Recurrent Neural Networks |
Authors | Philip Warrick, Masun Nabhan Homsi |
Abstract | Sleep disorders are implicated in a growing number of health problems. In this paper, we present a signal-processing/machine learning approach to detecting arousals in the multi-channel polysomnographic recordings of the Physionet/CinC Challenge2018 dataset. Methods: Our network architecture consists of two components. Inputs were presented to a Scattering Transform (ST) representation layer which fed a recurrent neural network for sequence learning using three layers of Long Short-Term Memory (LSTM). The STs were calculated for each signal with downsampling parameters chosen to give approximately 1 s time resolution, resulting in an eighteen-fold data reduction. The LSTM layers then operated at this downsampled rate. Results: The proposed approach detected arousal regions on the 10% random sample of the hidden test set with an AUROC of 88.0% and an AUPRC of 42.1%. |
Tasks | Sleep Arousal Detection |
Published | 2018-10-21 |
URL | http://arxiv.org/abs/1810.08875v1 |
http://arxiv.org/pdf/1810.08875v1.pdf | |
PWC | https://paperswithcode.com/paper/sleep-arousal-detection-from-polysomnography |
Repo | |
Framework | |
Learning to Search via Retrospective Imitation
Title | Learning to Search via Retrospective Imitation |
Authors | Jialin Song, Ravi Lanka, Albert Zhao, Aadyot Bhatnagar, Yisong Yue, Masahiro Ono |
Abstract | We study the problem of learning a good search policy for combinatorial search spaces. We propose retrospective imitation learning, which, after initial training by an expert, improves itself by learning from \textit{retrospective inspections} of its own roll-outs. That is, when the policy eventually reaches a feasible solution in a combinatorial search tree after making mistakes and backtracks, it retrospectively constructs an improved search trace to the solution by removing backtracks, which is then used to further train the policy. A key feature of our approach is that it can iteratively scale up, or transfer, to larger problem sizes than those solved by the initial expert demonstrations, thus dramatically expanding its applicability beyond that of conventional imitation learning. We showcase the effectiveness of our approach on a range of tasks, including synthetic maze solving and combinatorial problems expressed as integer programs. |
Tasks | Imitation Learning |
Published | 2018-04-03 |
URL | https://arxiv.org/abs/1804.00846v4 |
https://arxiv.org/pdf/1804.00846v4.pdf | |
PWC | https://paperswithcode.com/paper/learning-to-search-via-retrospective |
Repo | |
Framework | |
Comparing CNN and LSTM character-level embeddings in BiLSTM-CRF models for chemical and disease named entity recognition
Title | Comparing CNN and LSTM character-level embeddings in BiLSTM-CRF models for chemical and disease named entity recognition |
Authors | Zenan Zhai, Dat Quoc Nguyen, Karin Verspoor |
Abstract | We compare the use of LSTM-based and CNN-based character-level word embeddings in BiLSTM-CRF models to approach chemical and disease named entity recognition (NER) tasks. Empirical results over the BioCreative V CDR corpus show that the use of either type of character-level word embeddings in conjunction with the BiLSTM-CRF models leads to comparable state-of-the-art performance. However, the models using CNN-based character-level word embeddings have a computational performance advantage, increasing training time over word-based models by 25% while the LSTM-based character-level word embeddings more than double the required training time. |
Tasks | Named Entity Recognition, Word Embeddings |
Published | 2018-08-25 |
URL | http://arxiv.org/abs/1808.08450v1 |
http://arxiv.org/pdf/1808.08450v1.pdf | |
PWC | https://paperswithcode.com/paper/comparing-cnn-and-lstm-character-level |
Repo | |
Framework | |
Measurement-based adaptation protocol with quantum reinforcement learning
Title | Measurement-based adaptation protocol with quantum reinforcement learning |
Authors | F. Albarrán-Arriagada, J. C. Retamal, E. Solano, L. Lamata |
Abstract | Machine learning employs dynamical algorithms that mimic the human capacity to learn, where the reinforcement learning ones are among the most similar to humans in this respect. On the other hand, adaptability is an essential aspect to perform any task efficiently in a changing environment, and it is fundamental for many purposes, such as natural selection. Here, we propose an algorithm based on successive measurements to adapt one quantum state to a reference unknown state, in the sense of achieving maximum overlap. The protocol naturally provides many identical copies of the reference state, such that in each measurement iteration more information about it is obtained. In our protocol, we consider a system composed of three parts, the “environment” system, which provides the reference state copies; the register, which is an auxiliary subsystem that interacts with the environment to acquire information from it; and the agent, which corresponds to the quantum state that is adapted by digital feedback with input corresponding to the outcome of the measurements on the register. With this proposal we can achieve an average fidelity between the environment and the agent of more than $90% $ with less than $30$ iterations of the protocol. In addition, we extend the formalism to $ d $-dimensional states, reaching an average fidelity of around $80% $ in less than $400$ iterations for $d=$ 11, for a variety of genuinely quantum and semiclassical states. This work paves the way for the development of quantum reinforcement learning protocols using quantum data and for the future deployment of semi-autonomous quantum systems. |
Tasks | |
Published | 2018-03-14 |
URL | http://arxiv.org/abs/1803.05340v2 |
http://arxiv.org/pdf/1803.05340v2.pdf | |
PWC | https://paperswithcode.com/paper/measurement-based-adaptation-protocol-with-1 |
Repo | |
Framework | |
Feature Based Framework to Detect Diseases, Tumor, and Bleeding in Wireless Capsule Endoscopy
Title | Feature Based Framework to Detect Diseases, Tumor, and Bleeding in Wireless Capsule Endoscopy |
Authors | Omid Haji Maghsoudi, Mahdi Alizadeh |
Abstract | Studying animal locomotion improves our understanding of motor control and aids in the treatment of motor impairment. Mice are a premier model of human disease and are the model system of choice for much of basic neuroscience. High frame rates (250 Hz) are needed to quantify the kinematics of these running rodents. Manual tracking, especially for multiple markers, becomes time-consuming and impossible. Therefore, an automated method is necessary. We propose a method to track the paws of the animal in the following manner: first, segmenting all the possible paws based on color; second, classifying the segmented objects using a support vector machine (SVM) and neural network (NN); third, classifying the objects using the kinematic features of the running animal, coupled with texture features from earlier frames; and finally, detecting and handling collisions to assure the correctness of labelled paws. The proposed method is validated in sixty 1,000 frame video sequences (4 seconds) captured by four cameras from five mice. The total sensitivity for tracking of the front and hind paw is 99.70% using the SVM classifier and 99.76% using the NN classifier. In addition, we show the feasibility of 3D reconstruction using the four camera system. |
Tasks | 3D Reconstruction |
Published | 2018-01-27 |
URL | http://arxiv.org/abs/1802.02232v1 |
http://arxiv.org/pdf/1802.02232v1.pdf | |
PWC | https://paperswithcode.com/paper/feature-based-framework-to-detect-diseases |
Repo | |
Framework | |
Stochastic Channel Decorrelation Network and Its Application to Visual Tracking
Title | Stochastic Channel Decorrelation Network and Its Application to Visual Tracking |
Authors | Jie Guo, Tingfa Xu, Shenwang Jiang, Ziyi Shen |
Abstract | Deep convolutional neural networks (CNNs) have dominated many computer vision domains because of their great power to extract good features automatically. However, many deep CNNs-based computer vison tasks suffer from lack of training data while there are millions of parameters in the deep models. Obviously, these two biphase violation facts will result in parameter redundancy of many poorly designed deep CNNs. Therefore, we look deep into the existing CNNs and find that the redundancy of network parameters comes from the correlation between features in different channels within a convolutional layer. To solve this problem, we propose the stochastic channel decorrelation (SCD) block which, in every iteration, randomly selects multiple pairs of channels within a convolutional layer and calculates their normalized cross correlation (NCC). Then a squared max-margin loss is proposed as the objective of SCD to suppress correlation and keep diversity between channels explicitly. The proposed SCD is very flexible and can be applied to any current existing CNN models simply. Based on the SCD and the Fully-Convolutional Siamese Networks, we proposed a visual tracking algorithm to verify the effectiveness of SCD. |
Tasks | Visual Tracking |
Published | 2018-07-03 |
URL | http://arxiv.org/abs/1807.01103v2 |
http://arxiv.org/pdf/1807.01103v2.pdf | |
PWC | https://paperswithcode.com/paper/stochastic-channel-decorrelation-network-and |
Repo | |
Framework | |
Fast Dynamic Convolutional Neural Networks for Visual Tracking
Title | Fast Dynamic Convolutional Neural Networks for Visual Tracking |
Authors | Zhiyan Cui, Na Lu |
Abstract | Most of the existing tracking methods based on CNN(convolutional neural networks) are too slow for real-time application despite the excellent tracking precision compared with the traditional ones. In this paper, a fast dynamic visual tracking algorithm combining CNN based MDNet(Multi-Domain Network) and RoIAlign was developed. The major problem of MDNet also lies in the time efficiency. Considering the computational complexity of MDNet is mainly caused by the large amount of convolution operations and fine-tuning of the network during tracking, a RoIPool layer which could conduct the convolution over the whole image instead of each RoI is added to accelerate the convolution and a new strategy of fine-tuning the fully-connected layers is used to accelerate the update. With RoIPool employed, the computation speed has been increased but the tracking precision has dropped simultaneously. RoIPool could lose some positioning precision because it can not handle locations represented by floating numbers. So RoIAlign, instead of RoIPool, which can process floating numbers of locations by bilinear interpolation has been added to the network. The results show the target localization precision has been improved and it hardly increases the computational cost. These strategies can accelerate the processing and make it 7x faster than MDNet with very low impact on precision and it can run at around 7 fps. The proposed algorithm has been evaluated on two benchmarks: OTB100 and VOT2016, on which high precision and speed have been obtained. The influence of the network structure and training data are also discussed with experiments. |
Tasks | Visual Tracking |
Published | 2018-06-29 |
URL | http://arxiv.org/abs/1807.03132v2 |
http://arxiv.org/pdf/1807.03132v2.pdf | |
PWC | https://paperswithcode.com/paper/fast-dynamic-convolutional-neural-networks |
Repo | |
Framework | |
Constrained Image Generation Using Binarized Neural Networks with Decision Procedures
Title | Constrained Image Generation Using Binarized Neural Networks with Decision Procedures |
Authors | Svyatoslav Korneev, Nina Narodytska, Luca Pulina, Armando Tacchella, Nikolaj Bjorner, Mooly Sagiv |
Abstract | We consider the problem of binary image generation with given properties. This problem arises in a number of practical applications, including generation of artificial porous medium for an electrode of lithium-ion batteries, for composed materials, etc. A generated image represents a porous medium and, as such, it is subject to two sets of constraints: topological constraints on the structure and process constraints on the physical process over this structure. To perform image generation we need to define a mapping from a porous medium to its physical process parameters. For a given geometry of a porous medium, this mapping can be done by solving a partial differential equation (PDE). However, embedding a PDE solver into the search procedure is computationally expensive. We use a binarized neural network to approximate a PDE solver. This allows us to encode the entire problem as a logical formula. Our main contribution is that, for the first time, we show that this problem can be tackled using decision procedures. Our experiments show that our model is able to produce random constrained images that satisfy both topological and process constraints. |
Tasks | Image Generation |
Published | 2018-02-24 |
URL | http://arxiv.org/abs/1802.08795v1 |
http://arxiv.org/pdf/1802.08795v1.pdf | |
PWC | https://paperswithcode.com/paper/constrained-image-generation-using-binarized |
Repo | |
Framework | |
Scaling shared model governance via model splitting
Title | Scaling shared model governance via model splitting |
Authors | Miljan Martic, Jan Leike, Andrew Trask, Matteo Hessel, Shane Legg, Pushmeet Kohli |
Abstract | Currently the only techniques for sharing governance of a deep learning model are homomorphic encryption and secure multiparty computation. Unfortunately, neither of these techniques is applicable to the training of large neural networks due to their large computational and communication overheads. As a scalable technique for shared model governance, we propose splitting deep learning model between multiple parties. This paper empirically investigates the security guarantee of this technique, which is introduced as the problem of model completion: Given the entire training data set or an environment simulator, and a subset of the parameters of a trained deep learning model, how much training is required to recover the model’s original performance? We define a metric for evaluating the hardness of the model completion problem and study it empirically in both supervised learning on ImageNet and reinforcement learning on Atari and DeepMind~Lab. Our experiments show that (1) the model completion problem is harder in reinforcement learning than in supervised learning because of the unavailability of the trained agent’s trajectories, and (2) its hardness depends not primarily on the number of parameters of the missing part, but more so on their type and location. Our results suggest that model splitting might be a feasible technique for shared model governance in some settings where training is very expensive. |
Tasks | |
Published | 2018-12-14 |
URL | http://arxiv.org/abs/1812.05979v1 |
http://arxiv.org/pdf/1812.05979v1.pdf | |
PWC | https://paperswithcode.com/paper/scaling-shared-model-governance-via-model |
Repo | |
Framework | |
Sequence Alignment with Dirichlet Process Mixtures
Title | Sequence Alignment with Dirichlet Process Mixtures |
Authors | Ieva Kazlauskaite, Ivan Ustyuzhaninov, Carl Henrik Ek, Neill D. F. Campbell |
Abstract | We present a probabilistic model for unsupervised alignment of high-dimensional time-warped sequences based on the Dirichlet Process Mixture Model (DPMM). We follow the approach introduced in (Kazlauskaite, 2018) of simultaneously representing each data sequence as a composition of a true underlying function and a time-warping, both of which are modelled using Gaussian processes (GPs) (Rasmussen, 2005), and aligning the underlying functions using an unsupervised alignment method. In (Kazlauskaite, 2018) the alignment is performed using the GP latent variable model (GP-LVM) (Lawrence, 2005) as a model of sequences, while our main contribution is extending this approach to using DPMM, which allows us to align the sequences temporally and cluster them at the same time. We show that the DPMM achieves competitive results in comparison to the GP-LVM on synthetic and real-world data sets, and discuss the different properties of the estimated underlying functions and the time-warps favoured by these models. |
Tasks | Gaussian Processes |
Published | 2018-11-26 |
URL | http://arxiv.org/abs/1811.10689v1 |
http://arxiv.org/pdf/1811.10689v1.pdf | |
PWC | https://paperswithcode.com/paper/sequence-alignment-with-dirichlet-process |
Repo | |
Framework | |
Horizon: Facebook’s Open Source Applied Reinforcement Learning Platform
Title | Horizon: Facebook’s Open Source Applied Reinforcement Learning Platform |
Authors | Jason Gauci, Edoardo Conti, Yitao Liang, Kittipat Virochsiri, Yuchen He, Zachary Kaden, Vivek Narayanan, Xiaohui Ye, Zhengxing Chen, Scott Fujimoto |
Abstract | In this paper we present Horizon, Facebook’s open source applied reinforcement learning (RL) platform. Horizon is an end-to-end platform designed to solve industry applied RL problems where datasets are large (millions to billions of observations), the feedback loop is slow (vs. a simulator), and experiments must be done with care because they don’t run in a simulator. Unlike other RL platforms, which are often designed for fast prototyping and experimentation, Horizon is designed with production use cases as top of mind. The platform contains workflows to train popular deep RL algorithms and includes data preprocessing, feature transformation, distributed training, counterfactual policy evaluation, optimized serving, and a model-based data understanding tool. We also showcase and describe real examples where reinforcement learning models trained with Horizon significantly outperformed and replaced supervised learning systems at Facebook. |
Tasks | |
Published | 2018-11-01 |
URL | https://arxiv.org/abs/1811.00260v5 |
https://arxiv.org/pdf/1811.00260v5.pdf | |
PWC | https://paperswithcode.com/paper/horizon-facebooks-open-source-applied |
Repo | |
Framework | |
State-aware Anti-drift Robust Correlation Tracking
Title | State-aware Anti-drift Robust Correlation Tracking |
Authors | Yuqi Han, Chenwei Deng, Zengshuo Zhang, Jinghong Nan, Baojun Zhao |
Abstract | Correlation filter (CF) based trackers have aroused increasing attentions in visual tracking field due to the superior performance on several datasets while maintaining high running speed. For each frame, an ideal filter is trained in order to discriminate the target from its surrounding background. Considering that the target always undergoes external and internal interference during tracking procedure, the trained filter should take consideration of not only the external distractions but also the target appearance variation synchronously. To this end, we present a State-aware Anti-drift Tracker (SAT) in this paper, which jointly model the discrimination and reliability information in filter learning. Specifically, global context patches are incorporated into filter training stage to better distinguish the target from backgrounds. Meanwhile, a color-based reliable mask is learned to encourage the filter to focus on more reliable regions suitable for tracking. We show that the proposed optimization problem could be efficiently solved using Alternative Direction Method of Multipliers and fully carried out in Fourier domain. Extensive experiments are conducted on OTB-100 datasets to compare the SAT tracker (both hand-crafted feature and CNN feature) with other relevant state-of-the-art methods. Both quantitative and qualitative evaluations further demonstrate the effectiveness and robustness of the proposed work. |
Tasks | Visual Tracking |
Published | 2018-06-28 |
URL | http://arxiv.org/abs/1806.10759v1 |
http://arxiv.org/pdf/1806.10759v1.pdf | |
PWC | https://paperswithcode.com/paper/state-aware-anti-drift-robust-correlation |
Repo | |
Framework | |
Optimal conditions for connectedness of discretized sets
Title | Optimal conditions for connectedness of discretized sets |
Authors | Boris Brimkov, Valentin E. Brimkov |
Abstract | Constructing a discretization of a given set is a major problem in various theoretical and applied disciplines. An offset discretization of a set $X$ is obtained by taking the integer points inside a closed neighborhood of $X$ of a certain radius. In this note we determine a minimum threshold for the offset radius, beyond which the discretization of a disconnected set is always connected. The results hold for a broad class of disconnected and unbounded subsets of $R^n$, and generalize several previous results. Algorithmic aspects and possible applications are briefly discussed. |
Tasks | |
Published | 2018-08-09 |
URL | http://arxiv.org/abs/1808.03053v1 |
http://arxiv.org/pdf/1808.03053v1.pdf | |
PWC | https://paperswithcode.com/paper/optimal-conditions-for-connectedness-of |
Repo | |
Framework | |
High Speed Kernelized Correlation Filters without Boundary Effect
Title | High Speed Kernelized Correlation Filters without Boundary Effect |
Authors | Ming Tang, Linyu Zheng, Bin Yu, Jinqiao Wang |
Abstract | Recently, correlation filter based trackers (CF trackers) have attracted much attention in vision community because of their top performance in both location and speed. However, the boundary effect imposed by the periodic assumption for the efficient optimization seriously limits their location accuracy. Although there existed many modern works to relax the boundary effect of CF trackers, they all are not able to eliminate the boundary effect thoroughly as well as exploit the kernel trick to improve their location accuracy, and their speeds are reduced greatly. Either relaxing the boundary effect or being able to exploit kernel trick to improve the accuracy, and either relaxing the boundary effect or keeping CF trackers running at high speed have been two dilemmas in the society of visual tracking. To solve these problems, in this paper, we propose a high speed kernel correlation filter without the boundary effect (nBEKCF). Unlike all current CF trackers which exploited real and virtual image patches to train their regression functions, we construct a set of non-orthogonal bases with a group of circulant basic samples and utilize a function defined in Hilbert space and a set of densely sampled, totally real patches to regress a Gaussian goal. This way, the boundary effect is eliminated thoroughly in theory and the kernel trick can be employed naturally. To ensure nBEKCF runs at high speed, we present two efficient algorithms, ACSII and CCIM, to significantly accelerate the evaluation of kernel matrix without employing FFT. By exploiting the circulant structure of basic samples, the efficiency of CCIM in evaluating correlation exceeds that of FFT remarkably. Preliminary experimental results on two public datasets, OTB2013 and OTB2015, show that, without bells and whistles, nBEKCF outperforms representative trackers with hand-crafted features, in the meanwhile, runs at 70 fps on average. |
Tasks | Visual Tracking |
Published | 2018-06-17 |
URL | http://arxiv.org/abs/1806.06406v3 |
http://arxiv.org/pdf/1806.06406v3.pdf | |
PWC | https://paperswithcode.com/paper/high-speed-kernelized-correlation-filters |
Repo | |
Framework | |