检索结果-内蒙古大学图书馆

Who is killed by police: Introducing supervised attention for hierarchical LSTMs

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Nguyen, Minh Nguyen, Thien Huu Hanoi University of Science and Technology Hanoi Viet Nam Montreal Institute for Learning Algorithms University of Montreal Canada Department of Computer and Information Science University of Oregon United States

Finding names of people killed by police has become increasingly important as police shootings get more and more public attention (police killing detection). Unfortunately, there has been not much work in the literature addressing this problem. The early work in this field (Keith et al., 2017) proposed a distant supervision framework based on Expectation Maximization (EM) to deal with the multiple appearances of the names in documents. However, such EM-based framework cannot take full advantages of deep learning models, necessitating the use of handdesigned features to improve the detection performance. In this work, we present a novel deep learning method to solve the problem of police killing recognition. The proposed method relies on hierarchical LSTMs to model the multiple sentences that contain the person names of interests, and introduce supervised attention mechanisms based on semantical word lists and dependency trees to upweight the important contextual words. Our experiments demonstrate the benefits of the proposed model and yield the state-of-the-art performance for police killing detection. Copyright © 2018, The Authors. All rights reserved.

关键词： Law enforcement

How can deep learning advance computational modeling of sensory information processing?

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Thompson, Jessica A.F. Bengio, Yoshua Formisano, Elia Schönwiesner, Marc International Laboratory for Brain Music and Sound University of Montreal Canada Montreal Institute for Learning Algorithms Montreal Canada Department of Cognitive Neuroscience Maastricht University Maastricht Netherlands Institute for Biology Leipzig University Leipzig Germany

Deep learning, computational neuroscience, and cognitive science have overlapping goals related to understanding intelligence such that perception and behaviour can be simulated in computational systems. In neuroimaging, machine learning methods have been used to test computational models of sensory information processing. Recently, these model comparison techniques have been used to evaluate deep neural networks (DNNs) as models of sensory information processing. However, the interpretation of such model evaluations is muddied by imprecise statistical conclusions. Here, we make explicit the types of conclusions that can be drawn from these existing model comparison techniques and how these conclusions change when the model in question is a DNN. We discuss how DNNs are amenable to new model comparison techniques that allow for stronger conclusions to be made about the computational mechanisms underlying sensory information processing. Copyright © 2018, The Authors. All rights reserved.

关键词： Deep neural networks

Regional and Temporal Patterns of Partisan Polarization during the COVID-19 Pandemic in the United States and Canada

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Yang, Zachary Imouza, Anne Touzel, Maximilian Puelma Amadoro, Cécile Desrosiers-Brisebois, Gabrielle Pelrine, Kellin Levy, Sacha Godbout, Jean-François Rabbany, Reihaneh School of Computer Science McGill University Canada Political Science McGill University Canada Montreal Institute for Learning Algorithms Canada Department of Political Science University of Montreal Canada

Public health measures were among the most polarizing topics debated online during the COVID-19 pandemic. Much of the discussion surrounded specific events, such as when and which particular interventions came into practise. In this work, we develop and apply an approach to measure subnational and eventdriven variation of partisan polarization and explore how these dynamics varied both across and within countries. We apply our measure to a dataset of over 50 million tweets posted during late 2020, a salient period of polarizing discourse in the early phase of the pandemic. In particular, we examine regional variations in both the United States and Canada, focusing on three specific health interventions: lockdowns, masks, and vaccines. We find that more politically conservative regions had higher levels of partisan polarization in both countries, especially in the US where a strong negative correlation exists between regional vaccination rates and degree of polarization in vaccine related discussions. We then analyze the timing, context, and profile of spikes in polarization, linking them to specific events discussed on social media across different regions in both countries. These typically last only a few days in duration, suggesting that online discussions reflect and could even drive changes in public opinion, which in the context of pandemic response impacts public health outcomes across different regions and over time. © 2024, CC BY-SA.

关键词： COVID-19

ChatPainter: Improving text to image generation using dialogue

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Sharma, Shikhar Suhubdy, Dendi Michalski, Vincent Kahou, Samira Ebrahimi Bengio, Yoshua Microsoft Research Montréal Canada Université de Montréal Montréal Canada Montreal Institute for Learning Algorithms Montréal Canada

Synthesizing realistic images from text descriptions on a dataset like Microsoft Common Objects in Context (MS COCO), where each image can contain several objects, is a challenging task. Prior work has used text captions to generate images. However, captions might not be informative enough to capture the entire image and insufficient for the model to be able to understand which objects in the images correspond to which words in the captions. We show that adding a dialogue that further describes the scene leads to significant improvement in the inception score and in the quality of generated images on the MS COCO dataset. Copyright © 2018, The Authors. All rights reserved.

关键词： Image enhancement

Adversarial network embedding

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Dai, Quanyu Li, Qiang Tang, Jian Wang, Dan Department of Computing Hong Kong Polytechnic University Hong Kong School of Software FEIT University of Technology Sydney Australia HEC Montreal Canada Montreal Institute for Learning Algorithms Canada

learning low-dimensional representations of networks has proved effective in a variety of tasks such as node classification, link prediction and network visualization. Existing methods can effectively encode different structural properties into the representations, such as neighborhood connectivity patterns, global structural role similarities and other highorder proximities. However, except for objectives to capture network structural properties, most of them suffer from lack of additional constraints for enhancing the robustness of representations. In this paper, we aim to exploit the strengths of generative adversarial networks in capturing latent features, and investigate its contribution in learning stable and robust graph representations. Specifically, we propose an Adversarial Network Embedding (ANE) framework, which leverages the adversarial learning principle to regularize the representation learning. It consists of two components, i.e., a structure preserving component and an adversarial learning component. The former component aims to capture network structural properties, while the latter contributes to learning robust representations by matching the posterior distribution of the latent representations to given priors. As shown by the empirical results, our method is competitive with or superior to state-of-the-art approaches on benchmark network embedding tasks. Copyright © 2017, The Authors. All rights reserved.

关键词： Network embeddings

Vgraph: A generative model for joint community detection and node representation learning

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Sun, Fan-Yun Qu, Meng Hoffmann, Jordan Huang, Chin-Wei Tang, Jian National Taiwan University Mila-Quebec Institute for Learning Algorithms Harvard University United States Element AI HEC Montreal CIFAR AI Research Chair

This paper focuses on two fundamental tasks of graph analysis: community detection and node representation learning, which capture the global and local structures of graphs, respectively. In the current literature, these two tasks are usually independently studied while they are actually highly correlated. We propose a probabilistic generative model called vGraph to learn community membership and node representation collaboratively. Specifically, we assume that each node can be represented as a mixture of communities, and each community is defined as a multinomial distribution over nodes. Both the mixing coefficients and the community distribution are parameterized by the low-dimensional representations of the nodes and communities. We designed an effective variational inference algorithm which regularizes the community membership of neighboring nodes to be similar in the latent space. Experimental results on multiple real-world graphs show that vGraph is very effective in both community detection and node representation learning, outperforming many competitive baselines in both tasks. We show that the framework of vGraph is quite flexible and can be easily extended to detect hierarchical communities. Copyright © 2019, The Authors. All rights reserved.

关键词： Population dynamics

Regularized binary network training

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Darabi, Sajad Belbahri, Mouloud Courbariaux, Matthieu Nia, Vahid Partovi Department of Computer Science University of California Los AngelesCA United States Department of Mathematics and Statistics University of Montreal MontrealQC Canada Montreal Institute of Learning Algorithms University of Montreal Montreal QC Canada Huawei Technologies Montreal Research Center MontrealQC Canada

The deployment of Deep neural networks (DNN) on edge devices has been difficult because they are resource hungry. Binary neural networks (BNN) help to alleviate the prohibitive resource requirements of DNN, where both activations and weights are limited to 1-bit. There is however a significant performance gap between BNNs and floating point DNNs. To reduce this gap, We propose an improved binary training method, by introducing a new regularization function that encourages training weights around binary values. In addition, we add trainable scaling factors to our regularization functions. We also introduce an improved approximation of the derivative of the sign activation function in the backward computation. These modifications are based on linear operations that are easily implementable into the binary training framework. We show experimental results on CIFAR-10 obtaining an accuracy of 87.4%, on AlexNet and 83.9% with DoReFa network. On ImageNet, our method also outperforms the traditional BNN method and XNOR-net, using AlexNet by a margin of 4% and 2% top-1 accuracy respectively. In other words, we significantly reduce the gap between BNNs and floating point DNNs. Copyright © 2018, The Authors. All rights reserved.

关键词： Deep neural networks

Structure-aware reinforcement learning for node-overload protection in mobile edge computing

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Jitani, Anirudha Mahajan, Aditya Zhu, Zhongwen Abou-Zeid, Hatem Fapi, Emmanuel Thepie Purmehdi, Hakimeh School of Computer Science McGill University Montreal Institute of Learning Algorithms Canada Department of Electrical and Computer Engineering McGill University Canada Global AI Accelerator Ericsson Montreal Canada Ericsson Ottawa Canada

Mobile Edge Computing (MEC) refers to the concept of placing computational capability and applications at the edge of the network, providing benefits such as reduced latency in handling client requests, reduced network congestion, and improved performance of applications. The performance and reliability of MEC are degraded significantly when one or several edge servers in the cluster are overloaded. Especially when a server crashes due to the overload, it causes service failures in MEC. In this work, an adaptive admission control policy to prevent edge node from getting overloaded is presented. This approach is based on a recently-proposed low complexity RL (Reinforcement learning) algorithm called SALMUT (Structure-Aware learning for Multiple Thresholds), which exploits the structure of the optimal admission control policy in multi-class queues for an average-cost setting. We extend the framework to work for node overload-protection problem in a discounted-cost setting. The proposed solution is validated using several scenarios mimicking real-world deployments in two different settings - computer simulations and a docker testbed. Our empirical evaluations show that the total discounted cost incurred by SALMUT is similar to state-of-the-art deep RL algorithms such as PPO (Proximal Policy Optimization) and A2C (Advantage Actor Critic) but requires an order of magnitude less time to train, outputs easily interpretable policy, and can be deployed in an online manner. © 2021, CC BY-NC-SA.

关键词： Markov processes

On orthogonality and learning recurrent networks with long term dependencies

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Vorontsov, Eugene Trabelsi, Chiheb Kadoury, Samuel Pal, Chris École Polytechnique de Montréal Montréal Canada Montreal Institute for Learning Algorithms Montréal Canada CHUM Research Center Montréal Canada

It is well known that it is challenging to train deep neural networks and recurrent neural networks for tasks that exhibit long term dependencies. The vanishing or exploding gradient problem is a well known issue associated with these challenges. One approach to addressing vanishing and exploding gradients is to use either soft or hard constraints on weight matrices so as to encourage or enforce orthogonality. Orthogonal matrices preserve gradient norm during backpropagation and may therefore be a desirable property. This paper explores issues with optimization convergence, speed and gradient stability when encouraging or enforcing orthogonality. To perform this analysis, we propose a weight matrix factorization and parameterization strategy through which we can bound matrix norms and therein control the degree of expansivity induced during backpropagation. We find that hard constraints on orthogonality can negatively affect the speed of convergence and model performance. Copyright © 2017, The Authors. All rights reserved.

关键词： Backpropagation