Paper Group ANR 620
Decompose-and-Integrate Learning for Multi-class Segmentation in Medical Images. Debiasing Personal Identities in Toxicity Classification. Constrained Restless Bandits for Dynamic Scheduling in Cyber-Physical Systems. Stochastic dynamical modeling of turbulent flows. Multi-Agent Manipulation via Locomotion using Hierarchical Sim2Real. Continual Rei …
Decompose-and-Integrate Learning for Multi-class Segmentation in Medical Images
| Title | Decompose-and-Integrate Learning for Multi-class Segmentation in Medical Images |
| Authors | Yizhe Zhang, Michael T. C. Ying, Danny Z. Chen |
| Abstract | Segmentation maps of medical images annotated by medical experts contain rich spatial information. In this paper, we propose to decompose annotation maps to learn disentangled and richer feature transforms for segmentation problems in medical images. Our new scheme consists of two main stages: decompose and integrate. Decompose: by annotation map decomposition, the original segmentation problem is decomposed into multiple segmentation sub-problems; these new segmentation sub-problems are modeled by training multiple deep learning modules, each with its own set of feature transforms. Integrate: a procedure summarizes the solutions of the modules in the previous stage; a final solution is then formed for the original segmentation problem. Multiple ways of annotation map decomposition are presented and a new end-to-end trainable K-to-1 deep network framework is developed for implementing our proposed “decompose-and-integrate” learning scheme. In experiments, we demonstrate that our decompose-and-integrate segmentation, utilizing state-of-the-art fully convolutional networks (e.g., DenseVoxNet in 3D and CUMedNet in 2D), improves segmentation performance on multiple 3D and 2D datasets. Ablation study confirms the effectiveness of our proposed learning scheme for medical images. |
| Tasks | |
| Published | 2019-06-07 |
| URL | https://arxiv.org/abs/1906.02901v1 |
| https://arxiv.org/pdf/1906.02901v1.pdf | |
| PWC | https://paperswithcode.com/paper/decompose-and-integrate-learning-for-multi |
| Repo | |
| Framework | |
Debiasing Personal Identities in Toxicity Classification
| Title | Debiasing Personal Identities in Toxicity Classification |
| Authors | Apik Ashod Zorian, Chandra Shekar Bikkanur |
| Abstract | As Machine Learning models continue to be relied upon for making automated decisions, the issue of model bias becomes more and more prevalent. In this paper, we approach training a text classifica-tion model and optimize on bias minimization by measuring not only the models performance on our dataset as a whole, but also how it performs across different subgroups. This requires measuring per-formance independently for different demographic subgroups and measuring bias by comparing them to results from the rest of our data. We show how unintended bias can be detected using these metrics and how removing bias from a dataset completely can result in worse results. |
| Tasks | |
| Published | 2019-08-14 |
| URL | https://arxiv.org/abs/1908.05757v1 |
| https://arxiv.org/pdf/1908.05757v1.pdf | |
| PWC | https://paperswithcode.com/paper/debiasing-personal-identities-in-toxicity |
| Repo | |
| Framework | |
Constrained Restless Bandits for Dynamic Scheduling in Cyber-Physical Systems
| Title | Constrained Restless Bandits for Dynamic Scheduling in Cyber-Physical Systems |
| Authors | Kesav Kaza, Rahul Meshram, Varun Mehta, S. N. Merchant |
| Abstract | Restless multi-armed bandits are a class of discrete time stochastic control problems which involve sequential decision making with a finite set of actions (called arms). This paper studies a class of constrained restless multi-armed bandits (CRMAB). The constraints are in the form of time varying set of actions (set of available arms). This variation can be either stochastic or semi-deterministic. Given a total set of arms, a fixed number of them can be chosen to be played in each decision interval. The play of each arm yields a state dependent reward. The current states of arms are partially observable through binary feedback signals from arms that are played. The current availability of arms is fully observable. The objective is to maximize long term cumulative reward. The uncertainty about future availability of arms along with partial state information makes this objective challenging. Applications for CRMAB abound in the domain of cyber-physical systems. This optimization problem is analyzed using Whittle’s index policy. To this end, a constrained restless single-armed bandit is studied. It is shown to admit a threshold-type optimal policy, and is also indexable. An algorithm to compute Whittle’s index is presented. Further, upper bounds on the value function are derived in order to estimate the degree of sub-optimality of various solutions. The simulation study compares the performance of Whittle’s index, modified Whittle’s index and myopic policies. |
| Tasks | Decision Making, Decision Making Under Uncertainty, Multi-Armed Bandits |
| Published | 2019-04-18 |
| URL | https://arxiv.org/abs/1904.08962v2 |
| https://arxiv.org/pdf/1904.08962v2.pdf | |
| PWC | https://paperswithcode.com/paper/sequential-decision-making-under-uncertainty |
| Repo | |
| Framework | |
Stochastic dynamical modeling of turbulent flows
| Title | Stochastic dynamical modeling of turbulent flows |
| Authors | Armin Zare, Tryphon T. Georgiou, Mihailo R. Jovanović |
| Abstract | Advanced measurement techniques and high performance computing have made large data sets available for a wide range of turbulent flows that arise in engineering applications. Drawing on this abundance of data, dynamical models can be constructed to reproduce structural and statistical features of turbulent flows, opening the way to the design of effective model-based flow control strategies. This review describes a framework for completing second-order statistics of turbulent flows by models that are based on the Navier-Stokes equations linearized around the turbulent mean velocity. Systems theory and convex optimization are combined to address the inherent uncertainty in the dynamics and the statistics of the flow by seeking a suitable parsimonious correction to the prior linearized model. Specifically, dynamical couplings between states of the linearized model dictate structural constraints on the statistics of flow fluctuations. Thence, colored-in-time stochastic forcing that drives the linearized model is sought to account for and reconcile dynamics with available data (i.e., partially known second order statistics). The number of dynamical degrees of freedom that are directly affected by stochastic excitation is minimized as a measure of model parsimony. The spectral content of the resulting colored-in-time stochastic contribution can alternatively be seen to arise from a low-rank structural perturbation of the linearized dynamical generator, pointing to suitable dynamical corrections that may account for the absence of the nonlinear interactions in the linearized model. |
| Tasks | |
| Published | 2019-08-26 |
| URL | https://arxiv.org/abs/1908.09487v1 |
| https://arxiv.org/pdf/1908.09487v1.pdf | |
| PWC | https://paperswithcode.com/paper/stochastic-dynamical-modeling-of-turbulent |
| Repo | |
| Framework | |
Multi-Agent Manipulation via Locomotion using Hierarchical Sim2Real
| Title | Multi-Agent Manipulation via Locomotion using Hierarchical Sim2Real |
| Authors | Ofir Nachum, Michael Ahn, Hugo Ponte, Shixiang Gu, Vikash Kumar |
| Abstract | Manipulation and locomotion are closely related problems that are often studied in isolation. In this work, we study the problem of coordinating multiple mobile agents to exhibit manipulation behaviors using a reinforcement learning (RL) approach. Our method hinges on the use of hierarchical sim2real – a simulated environment is used to learn low-level goal-reaching skills, which are then used as the action space for a high-level RL controller, also trained in simulation. The full hierarchical policy is then transferred to the real world in a zero-shot fashion. The application of domain randomization during training enables the learned behaviors to generalize to real-world settings, while the use of hierarchy provides a modular paradigm for learning and transferring increasingly complex behaviors. We evaluate our method on a number of real-world tasks, including coordinated object manipulation in a multi-agent setting. See videos at https://sites.google.com/view/manipulation-via-locomotion |
| Tasks | |
| Published | 2019-08-13 |
| URL | https://arxiv.org/abs/1908.05224v2 |
| https://arxiv.org/pdf/1908.05224v2.pdf | |
| PWC | https://paperswithcode.com/paper/multi-agent-manipulation-via-locomotion-using |
| Repo | |
| Framework | |
Continual Reinforcement Learning deployed in Real-life using Policy Distillation and Sim2Real Transfer
| Title | Continual Reinforcement Learning deployed in Real-life using Policy Distillation and Sim2Real Transfer |
| Authors | René Traoré, Hugo Caselles-Dupré, Timothée Lesort, Te Sun, Natalia Díaz-Rodríguez, David Filliat |
| Abstract | We focus on the problem of teaching a robot to solve tasks presented sequentially, i.e., in a continual learning scenario. The robot should be able to solve all tasks it has encountered, without forgetting past tasks. We provide preliminary work on applying Reinforcement Learning to such setting, on 2D navigation tasks for a 3 wheel omni-directional robot. Our approach takes advantage of state representation learning and policy distillation. Policies are trained using learned features as input, rather than raw observations, allowing better sample efficiency. Policy distillation is used to combine multiple policies into a single one that solves all encountered tasks. |
| Tasks | Continual Learning, Representation Learning |
| Published | 2019-06-11 |
| URL | https://arxiv.org/abs/1906.04452v1 |
| https://arxiv.org/pdf/1906.04452v1.pdf | |
| PWC | https://paperswithcode.com/paper/continual-reinforcement-learning-deployed-in |
| Repo | |
| Framework | |
Semi-Supervised Deep Learning Using Improved Unsupervised Discriminant Projection
| Title | Semi-Supervised Deep Learning Using Improved Unsupervised Discriminant Projection |
| Authors | Xiao Han, Zihao Wang, Enmei Tu, Gunnam Suryanarayana, Jie Yang |
| Abstract | Deep learning demands a huge amount of well-labeled data to train the network parameters. How to use the least amount of labeled data to obtain the desired classification accuracy is of great practical significance, because for many real-world applications (such as medical diagnosis), it is difficult to obtain so many labeled samples. In this paper, modify the unsupervised discriminant projection algorithm from dimension reduction and apply it as a regularization term to propose a new semi-supervised deep learning algorithm, which is able to utilize both the local and nonlocal distribution of abundant unlabeled samples to improve classification performance. Experiments show that given dozens of labeled samples, the proposed algorithm can train a deep network to attain satisfactory classification results. |
| Tasks | Dimensionality Reduction, Medical Diagnosis |
| Published | 2019-12-19 |
| URL | https://arxiv.org/abs/1912.09147v1 |
| https://arxiv.org/pdf/1912.09147v1.pdf | |
| PWC | https://paperswithcode.com/paper/semi-supervised-deep-learning-using-improved |
| Repo | |
| Framework | |
Neural networks with redundant representation: detecting the undetectable
| Title | Neural networks with redundant representation: detecting the undetectable |
| Authors | Elena Agliari, Francesco Alemanno, Adriano Barra, Martino Centonze, Alberto Fachechi |
| Abstract | We consider a three-layer Sejnowski machine and show that features learnt via contrastive divergence have a dual representation as patterns in a dense associative memory of order P=4. The latter is known to be able to Hebbian-store an amount of patterns scaling as N^{P-1}, where N denotes the number of constituting binary neurons interacting P-wisely. We also prove that, by keeping the dense associative network far from the saturation regime (namely, allowing for a number of patterns scaling only linearly with N, while P>2) such a system is able to perform pattern recognition far below the standard signal-to-noise threshold. In particular, a network with P=4 is able to retrieve information whose intensity is O(1) even in the presence of a noise O(\sqrt{N}) in the large N limit. This striking skill stems from a redundancy representation of patterns – which is afforded given the (relatively) low-load information storage – and it contributes to explain the impressive abilities in pattern recognition exhibited by new-generation neural networks. The whole theory is developed rigorously, at the replica symmetric level of approximation, and corroborated by signal-to-noise analysis and Monte Carlo simulations. |
| Tasks | |
| Published | 2019-11-28 |
| URL | https://arxiv.org/abs/1911.12689v1 |
| https://arxiv.org/pdf/1911.12689v1.pdf | |
| PWC | https://paperswithcode.com/paper/neural-networks-with-redundant-representation |
| Repo | |
| Framework | |
Recurrent U-Net for Resource-Constrained Segmentation
| Title | Recurrent U-Net for Resource-Constrained Segmentation |
| Authors | Wei Wang, Kaicheng Yu, Joachim Hugonot, Pascal Fua, Mathieu Salzmann |
| Abstract | State-of-the-art segmentation methods rely on very deep networks that are not always easy to train without very large training datasets and tend to be relatively slow to run on standard GPUs. In this paper, we introduce a novel recurrent U-Net architecture that preserves the compactness of the original U-Net, while substantially increasing its performance to the point where it outperforms the state of the art on several benchmarks. We will demonstrate its effectiveness for several tasks, including hand segmentation, retina vessel segmentation, and road segmentation. We also introduce a large-scale dataset for hand segmentation. |
| Tasks | Hand Segmentation |
| Published | 2019-06-11 |
| URL | https://arxiv.org/abs/1906.04913v1 |
| https://arxiv.org/pdf/1906.04913v1.pdf | |
| PWC | https://paperswithcode.com/paper/recurrent-u-net-for-resource-constrained |
| Repo | |
| Framework | |
The Actor-Advisor: Policy Gradient With Off-Policy Advice
| Title | The Actor-Advisor: Policy Gradient With Off-Policy Advice |
| Authors | Hélène Plisnier, Denis Steckelmacher, Diederik M. Roijers, Ann Nowé |
| Abstract | Actor-critic algorithms learn an explicit policy (actor), and an accompanying value function (critic). The actor performs actions in the environment, while the critic evaluates the actor’s current policy. However, despite their stability and promising convergence properties, current actor-critic algorithms do not outperform critic-only ones in practice. We believe that the fact that the critic learns Q^pi, instead of the optimal Q-function Q*, prevents state-of-the-art robust and sample-efficient off-policy learning algorithms from being used. In this paper, we propose an elegant solution, the Actor-Advisor architecture, in which a Policy Gradient actor learns from unbiased Monte-Carlo returns, while being shaped (or advised) by the Softmax policy arising from an off-policy critic. The critic can be learned independently from the actor, using any state-of-the-art algorithm. Being advised by a high-quality critic, the actor quickly and robustly learns the task, while its use of the Monte-Carlo return helps overcome any bias the critic may have. In addition to a new Actor-Critic formulation, the Actor-Advisor, a method that allows an external advisory policy to shape a Policy Gradient actor, can be applied to many other domains. By varying the source of advice, we demonstrate the wide applicability of the Actor-Advisor to three other important subfields of RL: safe RL with backup policies, efficient leverage of domain knowledge, and transfer learning in RL. Our experimental results demonstrate the benefits of the Actor-Advisor compared to state-of-the-art actor-critic methods, illustrate its applicability to the three other application scenarios listed above, and show that many important challenges of RL can now be solved using a single elegant solution. |
| Tasks | Transfer Learning |
| Published | 2019-02-07 |
| URL | http://arxiv.org/abs/1902.02556v1 |
| http://arxiv.org/pdf/1902.02556v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-actor-advisor-policy-gradient-with-off |
| Repo | |
| Framework | |
Question Answering is a Format; When is it Useful?
| Title | Question Answering is a Format; When is it Useful? |
| Authors | Matt Gardner, Jonathan Berant, Hannaneh Hajishirzi, Alon Talmor, Sewon Min |
| Abstract | Recent years have seen a dramatic expansion of tasks and datasets posed as question answering, from reading comprehension, semantic role labeling, and even machine translation, to image and video understanding. With this expansion, there are many differing views on the utility and definition of “question answering” itself. Some argue that its scope should be narrow, or broad, or that it is overused in datasets today. In this opinion piece, we argue that question answering should be considered a format which is sometimes useful for studying particular phenomena, not a phenomenon or task in itself. We discuss when a task is correctly described as question answering, and when a task is usefully posed as question answering, instead of using some other format. |
| Tasks | Machine Translation, Question Answering, Reading Comprehension, Semantic Role Labeling, Video Understanding |
| Published | 2019-09-25 |
| URL | https://arxiv.org/abs/1909.11291v1 |
| https://arxiv.org/pdf/1909.11291v1.pdf | |
| PWC | https://paperswithcode.com/paper/question-answering-is-a-format-when-is-it |
| Repo | |
| Framework | |
Multi-Sentence Argument Linking
| Title | Multi-Sentence Argument Linking |
| Authors | Seth Ebner, Patrick Xia, Ryan Culkin, Kyle Rawlins, Benjamin Van Durme |
| Abstract | We introduce a dataset with annotated Roles Across Multiple Sentences (RAMS), consisting of over 9,000 annotated events. This enables the development of a novel span-based labeling framework that operates at the document level, which connects related ideas in sentence-level semantic role labeling and coreference resolution. We achieve 68.1 F1 on RAMS when given argument span boundaries and 73.2 F1 when also given gold event types. We additionally illustrate the applicability of the approach to the slot filling task in the Gun Violence Database. |
| Tasks | Coreference Resolution, Semantic Role Labeling, Slot Filling |
| Published | 2019-11-09 |
| URL | https://arxiv.org/abs/1911.03766v1 |
| https://arxiv.org/pdf/1911.03766v1.pdf | |
| PWC | https://paperswithcode.com/paper/multi-sentence-argument-linking |
| Repo | |
| Framework | |
Dialog State Tracking: A Neural Reading Comprehension Approach
| Title | Dialog State Tracking: A Neural Reading Comprehension Approach |
| Authors | Shuyang Gao, Abhishek Sethi, Sanchit Agarwal, Tagyoung Chung, Dilek Hakkani-Tur |
| Abstract | Dialog state tracking is used to estimate the current belief state of a dialog given all the preceding conversation. Machine reading comprehension, on the other hand, focuses on building systems that read passages of text and answer questions that require some understanding of passages. We formulate dialog state tracking as a reading comprehension task to answer the question $what\ is\ the\ state\ of\ the\ current\ dialog?$ after reading conversational context. In contrast to traditional state tracking methods where the dialog state is often predicted as a distribution over a closed set of all the possible slot values within an ontology, our method uses a simple attention-based neural network to point to the slot values within the conversation. Experiments on MultiWOZ-2.0 cross-domain dialog dataset show that our simple system can obtain similar accuracies compared to the previous more complex methods. By exploiting recent advances in contextual word embeddings, adding a model that explicitly tracks whether a slot value should be carried over to the next turn, and combining our method with a traditional joint state tracking method that relies on closed set vocabulary, we can obtain a joint-goal accuracy of $47.33%$ on the standard test split, exceeding current state-of-the-art by $11.75%$**. |
| Tasks | Machine Reading Comprehension, Reading Comprehension, Word Embeddings |
| Published | 2019-08-06 |
| URL | https://arxiv.org/abs/1908.01946v3 |
| https://arxiv.org/pdf/1908.01946v3.pdf | |
| PWC | https://paperswithcode.com/paper/dialog-state-tracking-a-neural-reading |
| Repo | |
| Framework | |
Electric Analog Circuit Design with Hypernetworks and a Differential Simulator
| Title | Electric Analog Circuit Design with Hypernetworks and a Differential Simulator |
| Authors | Michael Rotman, Lior Wolf |
| Abstract | The manual design of analog circuits is a tedious task of parameter tuning that requires hours of work by human experts. In this work, we make a significant step towards a fully automatic design method that is based on deep learning. The method selects the components and their configuration, as well as their numerical parameters. By contrast, the current literature methods are limited to the parameter fitting part only. A two-stage network is used, which first generates a chain of circuit components and then predicts their parameters. A hypernetwork scheme is used in which a weight generating network, which is conditioned on the circuit’s power spectrum, produces the parameters of a primal RNN network that places the components. A differential simulator is used for refining the numerical values of the components. We show that our model provides an efficient design solution, and is superior to alternative solutions. |
| Tasks | |
| Published | 2019-11-08 |
| URL | https://arxiv.org/abs/1911.03053v2 |
| https://arxiv.org/pdf/1911.03053v2.pdf | |
| PWC | https://paperswithcode.com/paper/electric-analog-circuit-design-with |
| Repo | |
| Framework | |
Optimizing the energy consumption of spiking neural networks for neuromorphic applications
| Title | Optimizing the energy consumption of spiking neural networks for neuromorphic applications |
| Authors | Martino Sorbaro, Qian Liu, Massimo Bortone, Sadique Sheik |
| Abstract | In the last few years, spiking neural networks have been demonstrated to perform on par with regular convolutional neural networks. Several works have proposed methods to convert a pre-trained CNN to a Spiking CNN without a significant sacrifice of performance. We demonstrate first that quantization-aware training of CNNs leads to better accuracy in SNNs. One of the benefits of converting CNNs to spiking CNNs is to leverage the sparse computation of SNNs and consequently perform equivalent computation at a lower energy consumption. Here we propose an efficient optimization strategy to train spiking networks at lower energy consumption, while maintaining similar accuracy levels. We demonstrate results on the MNIST-DVS and CIFAR-10 datasets. |
| Tasks | Quantization |
| Published | 2019-12-03 |
| URL | https://arxiv.org/abs/1912.01268v1 |
| https://arxiv.org/pdf/1912.01268v1.pdf | |
| PWC | https://paperswithcode.com/paper/optimizing-the-energy-consumption-of-spiking |
| Repo | |
| Framework | |
