Paper Group ANR 1486
Takens-inspired neuromorphic processor: a downsizing tool for random recurrent neural networks via feature extraction. Thresholding Bandit Problem with Both Duels and Pulls. Training on Synthetic Noise Improves Robustness to Natural Noise in Machine Translation. Two-stage WECC Composite Load Modeling: A Double Deep Q-Learning Networks Approach. Qui …
Takens-inspired neuromorphic processor: a downsizing tool for random recurrent neural networks via feature extraction
| Title | Takens-inspired neuromorphic processor: a downsizing tool for random recurrent neural networks via feature extraction |
| Authors | Bicky A. Marquez, Jose Suarez-Vargas, Bhavin J. Shastri |
| Abstract | We describe a new technique which minimizes the amount of neurons in the hidden layer of a random recurrent neural network (rRNN) for time series prediction. Merging Takens-based attractor reconstruction methods with machine learning, we identify a mechanism for feature extraction that can be leveraged to lower the network size. We obtain criteria specific to the particular prediction task and derive the scaling law of the prediction error. The consequences of our theory are demonstrated by designing a Takens-inspired hybrid processor, which extends a rRNN with a priori designed delay external memory. Our hybrid architecture is therefore designed including both, real and virtual nodes. Via this symbiosis, we show performance of the hybrid processor by stabilizing an arrhythmic neural model. Thanks to our obtained design rules, we can reduce the stabilizing neural network’s size by a factor of 15 with respect to a standard system. |
| Tasks | Time Series, Time Series Prediction |
| Published | 2019-07-06 |
| URL | https://arxiv.org/abs/1907.03122v1 |
| https://arxiv.org/pdf/1907.03122v1.pdf | |
| PWC | https://paperswithcode.com/paper/takens-inspired-neuromorphic-processor-a |
| Repo | |
| Framework | |
Thresholding Bandit Problem with Both Duels and Pulls
| Title | Thresholding Bandit Problem with Both Duels and Pulls |
| Authors | Yichong Xu, Xi Chen, Aarti Singh, Artur Dubrawski |
| Abstract | The Thresholding Bandit Problem (TBP) aims to find the set of arms with mean rewards greater than a given threshold. We consider a new setting of TBP, where in addition to pulling arms, one can also duel two arms and get the arm with a greater mean. In our motivating application from crowdsourcing, dueling two arms can be more cost and time efficient than direct pulls. We refer to this problem as TBP with Dueling Choices (TBP-DC). This paper provides an algorithm called Rank-Search (RS) for solving TBP-DC by alternating between ranking and binary search. We prove theoretical guarantees for RS, and also give lower bounds to show the optimality of it. Experiments show that RS outperforms previous baseline algorithms that only use pulls or duels. |
| Tasks | |
| Published | 2019-10-14 |
| URL | https://arxiv.org/abs/1910.06368v1 |
| https://arxiv.org/pdf/1910.06368v1.pdf | |
| PWC | https://paperswithcode.com/paper/thresholding-bandit-problem-with-both-duels |
| Repo | |
| Framework | |
Training on Synthetic Noise Improves Robustness to Natural Noise in Machine Translation
| Title | Training on Synthetic Noise Improves Robustness to Natural Noise in Machine Translation |
| Authors | Vladimir Karpukhin, Omer Levy, Jacob Eisenstein, Marjan Ghazvininejad |
| Abstract | We consider the problem of making machine translation more robust to character-level variation at the source side, such as typos. Existing methods achieve greater coverage by applying subword models such as byte-pair encoding (BPE) and character-level encoders, but these methods are highly sensitive to spelling mistakes. We show how training on a mild amount of random synthetic noise can dramatically improve robustness to these variations, without diminishing performance on clean text. We focus on translation performance on natural noise, as captured by frequent corrections in Wikipedia edit logs, and show that robustness to such noise can be achieved using a balanced diet of simple synthetic noises at training time, without access to the natural noise data or distribution. |
| Tasks | Machine Translation |
| Published | 2019-02-05 |
| URL | http://arxiv.org/abs/1902.01509v1 |
| http://arxiv.org/pdf/1902.01509v1.pdf | |
| PWC | https://paperswithcode.com/paper/training-on-synthetic-noise-improves |
| Repo | |
| Framework | |
Two-stage WECC Composite Load Modeling: A Double Deep Q-Learning Networks Approach
| Title | Two-stage WECC Composite Load Modeling: A Double Deep Q-Learning Networks Approach |
| Authors | Xinan Wang, Yishen Wang, Di Shi, Jianhui Wang, Zhiwei Wang |
| Abstract | With the increasing complexity of modern power systems, conventional dynamic load modeling with ZIP and induction motors (ZIP + IM) is no longer adequate to address the current load characteristic transitions. In recent years, the WECC composite load model (WECC CLM) has shown to effectively capture the dynamic load responses over traditional load models in various stability studies and contingency analyses. However, a detailed WECC CLM model typically has a high degree of complexity, with over one hundred parameters, and no systematic approach to identifying and calibrating these parameters. Enabled by the wide deployment of PMUs and advanced deep learning algorithms, proposed here is a double deep Q-learning network (DDQN)-based, two-stage load modeling framework for the WECC CLM. This two-stage method decomposes the complicated WECC CLM for more efficient identification and does not require explicit model details. In the first stage, the DDQN agent determines an accurate load composition. In the second stage, the parameters of the WECC CLM are selected from a group of Monte-Carlo simulations. The set of selected load parameters is expected to best approximate the true transient responses. The proposed framework is verified using an IEEE 39-bus test system on commercial simulation platforms. |
| Tasks | Q-Learning |
| Published | 2019-11-08 |
| URL | https://arxiv.org/abs/1911.04894v1 |
| https://arxiv.org/pdf/1911.04894v1.pdf | |
| PWC | https://paperswithcode.com/paper/two-stage-wecc-composite-load-modeling-a |
| Repo | |
| Framework | |
Quinoa: a Q-function You Infer Normalized Over Actions
| Title | Quinoa: a Q-function You Infer Normalized Over Actions |
| Authors | Jonas Degrave, Abbas Abdolmaleki, Jost Tobias Springenberg, Nicolas Heess, Martin Riedmiller |
| Abstract | We present an algorithm for learning an approximate action-value soft Q-function in the relative entropy regularised reinforcement learning setting, for which an optimal improved policy can be recovered in closed form. We use recent advances in normalising flows for parametrising the policy together with a learned value-function; and show how this combination can be used to implicitly represent Q-values of an arbitrary policy in continuous action space. Using simple temporal difference learning on the Q-values then leads to a unified objective for policy and value learning. We show how this approach considerably simplifies standard Actor-Critic off-policy algorithms, removing the need for a policy optimisation step. We perform experiments on a range of established reinforcement learning benchmarks, demonstrating that our approach allows for complex, multimodal policy distributions in continuous action spaces, while keeping the process of sampling from the policy both fast and exact. |
| Tasks | Normalising Flows |
| Published | 2019-11-05 |
| URL | https://arxiv.org/abs/1911.01831v1 |
| https://arxiv.org/pdf/1911.01831v1.pdf | |
| PWC | https://paperswithcode.com/paper/quinoa-a-q-function-you-infer-normalized-over |
| Repo | |
| Framework | |
Mesh Learning Using Persistent Homology on the Laplacian Eigenfunctions
| Title | Mesh Learning Using Persistent Homology on the Laplacian Eigenfunctions |
| Authors | Yunhao Zhang, Haowen Liu, Paul Rosen, Mustafa Hajij |
| Abstract | We use persistent homology along with the eigenfunctions of the Laplacian to study similarity amongst triangulated 2-manifolds. Our method relies on studying the lower-star filtration induced by the eigenfunctions of the Laplacian. This gives us a shape descriptor that inherits the rich information encoded in the eigenfunctions of the Laplacian. Moreover, the similarity between these descriptors can be easily computed using tools that are readily available in Topological Data Analysis. We provide experiments to illustrate the effectiveness of the proposed method. |
| Tasks | Topological Data Analysis |
| Published | 2019-04-21 |
| URL | http://arxiv.org/abs/1904.09639v2 |
| http://arxiv.org/pdf/1904.09639v2.pdf | |
| PWC | https://paperswithcode.com/paper/mesh-learning-using-persistent-homology-on |
| Repo | |
| Framework | |
Evaluating Explanation Without Ground Truth in Interpretable Machine Learning
| Title | Evaluating Explanation Without Ground Truth in Interpretable Machine Learning |
| Authors | Fan Yang, Mengnan Du, Xia Hu |
| Abstract | Interpretable Machine Learning (IML) has become increasingly important in many real-world applications, such as autonomous cars and medical diagnosis, where explanations are significantly preferred to help people better understand how machine learning systems work and further enhance their trust towards systems. However, due to the diversified scenarios and subjective nature of explanations, we rarely have the ground truth for benchmark evaluation in IML on the quality of generated explanations. Having a sense of explanation quality not only matters for assessing system boundaries, but also helps to realize the true benefits to human users in practical settings. To benchmark the evaluation in IML, in this article, we rigorously define the problem of evaluating explanations, and systematically review the existing efforts from state-of-the-arts. Specifically, we summarize three general aspects of explanation (i.e., generalizability, fidelity and persuasibility) with formal definitions, and respectively review the representative methodologies for each of them under different tasks. Further, a unified evaluation framework is designed according to the hierarchical needs from developers and end-users, which could be easily adopted for different scenarios in practice. In the end, open problems are discussed, and several limitations of current evaluation techniques are raised for future explorations. |
| Tasks | Interpretable Machine Learning, Medical Diagnosis |
| Published | 2019-07-16 |
| URL | https://arxiv.org/abs/1907.06831v2 |
| https://arxiv.org/pdf/1907.06831v2.pdf | |
| PWC | https://paperswithcode.com/paper/evaluating-explanation-without-ground-truth |
| Repo | |
| Framework | |
Understanding Neural Architecture Search Techniques
| Title | Understanding Neural Architecture Search Techniques |
| Authors | George Adam, Jonathan Lorraine |
| Abstract | Automatic methods for generating state-of-the-art neural network architectures without human experts have generated significant attention recently. This is because of the potential to remove human experts from the design loop which can reduce costs and decrease time to model deployment. Neural architecture search (NAS) techniques have improved significantly in their computational efficiency since the original NAS was proposed. This reduction in computation is enabled via weight sharing such as in Efficient Neural Architecture Search (ENAS). However, recently a body of work confirms our discovery that ENAS does not do significantly better than random search with weight sharing, contradicting the initial claims of the authors. We provide an explanation for this phenomenon by investigating the interpretability of the ENAS controller’s hidden state. We find models sampled from identical controller hidden states have no correlation with various graph similarity metrics, so no notion of structural similarity is learned. This failure mode implies the RNN controller does not condition on past architecture choices. Lastly, we propose a solution to this failure mode by forcing the controller’s hidden state to encode pasts decisions by training it with a memory buffer of previously sampled architectures. Doing this improves hidden state interpretability by increasing the correlation between controller hidden states and graph similarity metrics. |
| Tasks | Graph Similarity, Neural Architecture Search |
| Published | 2019-03-31 |
| URL | https://arxiv.org/abs/1904.00438v2 |
| https://arxiv.org/pdf/1904.00438v2.pdf | |
| PWC | https://paperswithcode.com/paper/understanding-neural-architecture-search |
| Repo | |
| Framework | |
k-t NEXT: Dynamic MR Image Reconstruction Exploiting Spatio-temporal Correlations
| Title | k-t NEXT: Dynamic MR Image Reconstruction Exploiting Spatio-temporal Correlations |
| Authors | Chen Qin, Jo Schlemper, Jinming Duan, Gavin Seegoolam, Anthony Price, Joseph Hajnal, Daniel Rueckert |
| Abstract | Dynamic magnetic resonance imaging (MRI) exhibits high correlations in k-space and time. In order to accelerate the dynamic MR imaging and to exploit k-t correlations from highly undersampled data, here we propose a novel deep learning based approach for dynamic MR image reconstruction, termed k-t NEXT (k-t NEtwork with X-f Transform). In particular, inspired by traditional methods such as k-t BLAST and k-t FOCUSS, we propose to reconstruct the true signals from aliased signals in x-f domain to exploit the spatio-temporal redundancies. Building on that, the proposed method then learns to recover the signals by alternating the reconstruction process between the x-f space and image space in an iterative fashion. This enables the network to effectively capture useful information and jointly exploit spatio-temporal correlations from both complementary domains. Experiments conducted on highly undersampled short-axis cardiac cine MRI scans demonstrate that our proposed method outperforms the current state-of-the-art dynamic MR reconstruction approaches both quantitatively and qualitatively. |
| Tasks | Image Reconstruction |
| Published | 2019-07-22 |
| URL | https://arxiv.org/abs/1907.09425v1 |
| https://arxiv.org/pdf/1907.09425v1.pdf | |
| PWC | https://paperswithcode.com/paper/k-t-next-dynamic-mr-image-reconstruction |
| Repo | |
| Framework | |
Accelerating Deep Unsupervised Domain Adaptation with Transfer Channel Pruning
| Title | Accelerating Deep Unsupervised Domain Adaptation with Transfer Channel Pruning |
| Authors | Chaohui Yu, Jindong Wang, Yiqiang Chen, Zijing Wu |
| Abstract | Deep unsupervised domain adaptation (UDA) has recently received increasing attention from researchers. However, existing methods are computationally intensive due to the computation cost of Convolutional Neural Networks (CNN) adopted by most work. To date, there is no effective network compression method for accelerating these models. In this paper, we propose a unified Transfer Channel Pruning (TCP) approach for accelerating UDA models. TCP is capable of compressing the deep UDA model by pruning less important channels while simultaneously learning transferable features by reducing the cross-domain distribution divergence. Therefore, it reduces the impact of negative transfer and maintains competitive performance on the target task. To the best of our knowledge, TCP is the first approach that aims at accelerating deep UDA models. TCP is validated on two benchmark datasets-Office-31 and ImageCLEF-DA with two common backbone networks-VGG16 and ResNet50. Experimental results demonstrate that TCP achieves comparable or better classification accuracy than other comparison methods while significantly reducing the computational cost. To be more specific, in VGG16, we get even higher accuracy after pruning 26% floating point operations (FLOPs); in ResNet50, we also get higher accuracy on half of the tasks after pruning 12% FLOPs. We hope that TCP will open a new door for future research on accelerating transfer learning models. |
| Tasks | Domain Adaptation, Transfer Learning, Unsupervised Domain Adaptation |
| Published | 2019-03-25 |
| URL | http://arxiv.org/abs/1904.02654v1 |
| http://arxiv.org/pdf/1904.02654v1.pdf | |
| PWC | https://paperswithcode.com/paper/accelerating-deep-unsupervised-domain |
| Repo | |
| Framework | |
Particle reconstruction of volumetric particle image velocimetry with strategy of machine learning
| Title | Particle reconstruction of volumetric particle image velocimetry with strategy of machine learning |
| Authors | Qi Gao, Qijie Li, Shaowu Pan, Hongping Wang, Runjie Wei, Jinjun Wang |
| Abstract | Three-dimensional particle reconstruction with limited two-dimensional projects is an underdetermined inverse problem that the exact solution is often difficulty to be obtained. In general, approximate solutions can be obtained by optimization methods. In the current work, a practical particle reconstruction method based on convolutional neural network (CNN) is proposed. The proposed technique can refine the particle reconstruction from a very coarse initial guess of particle distribution from any traditional algebraic reconstruction technique (ART) based methods. Compared with available ART-based algorithms, the novel technique makes significant improvements in terms of reconstruction quality and at least an order of magnitude faster with dense particle concentration. |
| Tasks | |
| Published | 2019-09-16 |
| URL | https://arxiv.org/abs/1909.07815v1 |
| https://arxiv.org/pdf/1909.07815v1.pdf | |
| PWC | https://paperswithcode.com/paper/particle-reconstruction-of-volumetric |
| Repo | |
| Framework | |
Road scenes analysis in adverse weather conditions by polarization-encoded images and adapted deep learning
| Title | Road scenes analysis in adverse weather conditions by polarization-encoded images and adapted deep learning |
| Authors | Rachel Blin, Samia Ainouz, Stéphane Canu, Fabrice Meriaudeau |
| Abstract | Object detection in road scenes is necessary to develop both autonomous vehicles and driving assistance systems. Even if deep neural networks for recognition task have shown great performances using conventional images, they fail to detect objects in road scenes in complex acquisition situations. In contrast, polarization images, characterizing the light wave, can robustly describe important physical properties of the object even under poor illumination or strong reflections. This paper shows how non-conventional polarimetric imaging modality overcomes the classical methods for object detection especially in adverse weather conditions. The efficiency of the proposed method is mostly due to the high power of the polarimetry to discriminate any object by its reflective properties and on the use of deep neural networks for object detection. Our goal by this work, is to prove that polarimetry brings a real added value compared with RGB images for object detection. Experimental results on our own dataset composed of road scene images taken during adverse weather conditions show that polarimetry together with deep learning can improve the state-of-the-art by about 20% to 50% on different detection tasks. |
| Tasks | Autonomous Vehicles, Object Detection |
| Published | 2019-10-02 |
| URL | https://arxiv.org/abs/1910.04870v1 |
| https://arxiv.org/pdf/1910.04870v1.pdf | |
| PWC | https://paperswithcode.com/paper/road-scenes-analysis-in-adverse-weather |
| Repo | |
| Framework | |
Blurred Images Lead to Bad Local Minima
| Title | Blurred Images Lead to Bad Local Minima |
| Authors | Gal Katzhendler, Daphna Weinshall |
| Abstract | Blurred Images Lead to Bad Local Minima |
| Tasks | |
| Published | 2019-01-30 |
| URL | http://arxiv.org/abs/1901.10788v1 |
| http://arxiv.org/pdf/1901.10788v1.pdf | |
| PWC | https://paperswithcode.com/paper/blurred-images-lead-to-bad-local-minima |
| Repo | |
| Framework | |
Beyond Pairwise Comparisons in Social Choice: A Setwise Kemeny Aggregation Problem
| Title | Beyond Pairwise Comparisons in Social Choice: A Setwise Kemeny Aggregation Problem |
| Authors | Hugo Gilbert, Tom Portoleau, Olivier Spanjaard |
| Abstract | In this paper, we advocate the use of setwise contests for aggregating a set of input rankings into an output ranking. We propose a generalization of the Kemeny rule where one minimizes the number of k-wise disagreements instead of pairwise disagreements (one counts 1 disagreement each time the top choice in a subset of alternatives of cardinality at most k differs between an input ranking and the output ranking). After an algorithmic study of this k-wise Kemeny aggregation problem, we introduce a k-wise counterpart of the majority graph. It reveals useful to divide the aggregation problem into several sub-problems. We conclude with numerical tests. |
| Tasks | |
| Published | 2019-11-14 |
| URL | https://arxiv.org/abs/1911.06226v1 |
| https://arxiv.org/pdf/1911.06226v1.pdf | |
| PWC | https://paperswithcode.com/paper/beyond-pairwise-comparisons-in-social-choice |
| Repo | |
| Framework | |
Blockchain Intelligence: When Blockchain Meets Artificial Intelligence
| Title | Blockchain Intelligence: When Blockchain Meets Artificial Intelligence |
| Authors | Zibin Zheng, Hong-Ning Dai |
| Abstract | Blockchain is gaining extensive attention due to its provision of secure and decentralized resource sharing manner. However, the incumbent blockchain systems also suffer from a number of challenges in operational maintenance, quality assurance of smart contracts and malicious behaviour detection of blockchain data. The recent advances in artificial intelligence bring the opportunities in overcoming the above challenges. The integration of blockchain with artificial intelligence can be beneficial to enhance current blockchain systems. This article presents an introduction of the convergence of blockchain and artificial intelligence (namely blockchain intelligence). This article also gives a case study to further demonstrate the feasibility of blockchain intelligence and point out the future directions. |
| Tasks | |
| Published | 2019-12-11 |
| URL | https://arxiv.org/abs/1912.06485v2 |
| https://arxiv.org/pdf/1912.06485v2.pdf | |
| PWC | https://paperswithcode.com/paper/blockchain-intelligence-when-blockchain-meets |
| Repo | |
| Framework | |
