检索结果-内蒙古大学图书馆

MARS: MARKOV MOLECULAR SAMPLING FOR MULTI-OBJECTIVE DRUG DISCOVERY 9

学校读者我要写书评

暂无评论

MARS: MARKOV MOLECULAR SAMPLING FOR MULTI-OBJECTIVE DRUG DIS...

9th International Conference on learning Representations, ICLR 2021

作者： Xie, Yutong Shi, Chence Zhou, Hao Yang, Yuwei Zhang, Weinan Yu, Yong Li, Lei ByteDance AI Lab Shanghai China University of Michigan Ann ArborMI United States Montréal Institute of Learning Algorithms Montreal Canada Department of Computer Science and Engineering Shanghai Jiao Tong University China

Searching for novel molecules with desired chemical properties is crucial in drug discovery. Existing work focuses on developing neural models to generate either molecular sequences or chemical graphs. However, it remains a big challenge to find novel and diverse compounds satisfying several properties. In this paper, we propose MARS, a method for multi-objective drug molecule discovery. MARS is based on the idea of generating the chemical candidates by iteratively editing fragments of molecular graphs. To search for high-quality candidates, it employs Markov chain Monte Carlo sampling (MCMC) on molecules with an annealing scheme and an adaptive proposal. To further improve sample efficiency, MARS uses a graph neural network (GNN) to represent and select candidate edits, where the GNN is trained on-the-fly with samples from MCMC. Experiments show that MARS achieves state-of-the-art performance in various multi-objective settings where molecular bio-activity, drug-likeness, and synthesizability are considered. Remarkably, in the most challenging setting where all four objectives are simultaneously optimized, our approach outperforms previous methods significantly in comprehensive evaluations. The code is available at https://***/yutxie/mars. © 2021 ICLR 2021 - 9th International Conference on learning Representations. All rights reserved.

关键词： Graph neural networks

On the iterative refinement of densely connected representation levels for semantic segmentation

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Casanova, Arantxa Cucurull, Guillem Drozdzal, Michal Romero, Adriana Bengio, Yoshua Montreal Institute for Learning Algorithms Computer Vision Center Barcelona Spain Facebook AI Research

State-of-the-art semantic segmentation approaches increase the receptive field of their models by using either a downsampling path composed of poolings/strided convolutions or successive dilated convolutions. However, it is not clear which operation leads to best results. In this paper, we systematically study the differences introduced by distinct receptive field enlargement methods and their impact on the performance of a novel architecture, called Fully Convolutional DenseResNet (FC-DRN). FC-DRN has a densely connected backbone composed of residual networks. Following standard image segmentation architectures, receptive field enlargement operations that change the representation level are interleaved among residual networks. This allows the model to exploit the benefits of both residual and dense connectivity patterns, namely: gradient flow, iterative refinement of representations, multi-scale feature combination and deep supervision. In order to highlight the potential of our model, we test it on the challenging CamVid urban scene understanding benchmark and make the following observations: 1) downsampling operations outperform dilations when the model is trained from scratch, 2) dilations are useful during the finetuning step of the model, 3) coarser representations require less refinement steps, and 4) ResNets (by model construction) are good regularizers, since they can reduce the model capacity when needed. Finally, we compare our architecture to alternative methods and report state-of-the-art result on the Camvid dataset, with at least twice fewer parameters. Copyright © 2018, The Authors. All rights reserved.

关键词： Convolution

Active reinforcement learning: Observing rewards at a cost

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Krueger, David Leike, Jan Evans, Owain Salvatier, John Montreal Institute for Learning Algorithms University of Montreal Canada Future of Humanity Institute University of Oxford United Kingdom AI Impacts Canada

Active reinforcement learning (ARL) is a variant on reinforcement learning where the agent does not observe the reward unless it chooses to pay a query cost c > 0. The central question of ARL is how to quantify the long-term value of reward information. Even in multi-armed bandits, computing the value of this information is intractable and we have to rely on heuristics. We propose and evaluate several heuristic approaches for ARL in multi-armed bandits and (tabular) Markov decision processes, and discuss and illustrate some challenging aspects of the ARL problem. Copyright © 2020, The Authors. All rights reserved.

关键词： Markov processes

Tell, Draw, and Repeat: Generating and Modifying Images Based on Continual Linguistic Instruction

学校读者我要写书评

暂无评论

Tell, Draw, and Repeat: Generating and Modifying Images Base...

International Conference on Computer Vision (ICCV)

作者： Alaaeldin El-Nouby Shikhar Sharma Hannes Schulz R Devon Hjelm Layla El Asri Samira Ebrahimi Kahou Yoshua Bengio Graham Taylor University of Guelph Vector Institute for Artificial Intelligence Microsoft Research Montreal Institute for Learning Algorithms University of Montreal Canadian Institute for Advanced Research

ISBN: (数字)9781728148038

ISBN: (纸本)9781728148045

Conditional text-to-image generation is an active area of research, with many possible applications. Existing research has primarily focused on generating a single image from available conditioning information in one step. One practical extension beyond one-step generation is a system that generates an image iteratively, conditioned on ongoing linguistic input or feedback. This is significantly more challenging than one-step generation tasks, as such a system must understand the contents of its generated images with respect to the feedback history, the current feedback, as well as the interactions among concepts present in the feedback history. In this work, we present a recurrent image generation model which takes into account both the generated output up to the current step as well as all past instructions for generation. We show that our model is able to generate the background, add new objects, and apply simple transformations to existing objects. We believe our approach is an important step toward interactive generation. Code and data is available at: https://***/en-us/research/project/generative-neural-visual-artist-geneva/.

关键词： Task analysis Linguistics Image generation Generators Visualization History Gallium nitride

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Mallet, Vincent Oliver, Carlos G. Hamilton, William L. Pasteur Institute Les Mines-Paristech Department of Computer Science McGill University Montreal Institute for Learning Algorithms

Graph are a ubiquitous data representation, as they represent a flexible and compact representation. For instance, the 3D structure of RNA can be efficiently represented as 2.5D graphs, graphs whose nodes are nucleotides and edges represent chemical interactions. In this setting, we have biological evidence of the similarity between the edge types, as some chemical interactions are more similar than others. Machine learning on graphs have recently experienced a breakthrough with the introduction of Graph Neural Networks. This algorithm can be framed as a message passing algorithm between graph nodes over graph edges. These messages can depend on the edge type they are transmitted through, but no method currently constrains how a message is altered when the edge type changes. Motivated by the RNA use case, in this project we introduce a graph neural network layer which can leverage prior information about similarities between edges. We show that despite the theoretical appeal of including this similarity prior, the empirical performance is not enhanced on the tasks and datasets we include here. © 2021, CC BY-NC-SA.

关键词： Graph neural networks

A survey of mobile computing for the visually impaired

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Weiss, Martin Luck, Margaux Girgis, Roger Pal, Chris Cohen, Joseph Paul Montreal Institute for Learning Algorithms Université de Montréal Polytechnique Montréal McGill University

The number of visually impaired or blind (VIB) people in the world is estimated at several hundred million[4]. Based on a series of interviews with the VIB and developers of assistive technology, this paper provides a survey of machine-learning based mobile applications and identifies the most relevant applications. We discuss the functionality of these apps, how they align with the needs and requirements of the VIB users, and how they can be improved with techniques such as federated learning and model compression. As a result of this study we identify promising future directions of research in mobile perception, micro-navigation, and content-summarization. Copyright © 2018, The Authors. All rights reserved.

关键词： Surveys

Distinction Maximization Loss: Efficiently Improving Out-of-Distribution Detection and Uncertainty Estimation by Replacing the Loss and Calibrating

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Macêdo, David Zanchettin, Cleber Ludermir, Teresa Centro de Informática Universidade Federal de Pernambuco Brazil Montreal Institute for Learning Algorithms University of Montreal Canada

Building robust deterministic neural networks remains a challenge. On the one hand, some approaches improve out-of-distribution detection at the cost of reducing classification accuracy in some situations. On the other hand, some methods simultaneously increase classification accuracy, uncertainty estimation, and out-of-distribution detection at the expense of reducing the inference efficiency. In this paper, we propose training deterministic neural networks using our DisMax loss, which works as a drop-in replacement for the usual SoftMax loss (i.e., the combination of the linear output layer, the SoftMax activation, and the cross-entropy loss). Starting from the IsoMax+ loss, we create each logit based on the distances to all prototypes, rather than just the one associated with the correct class. We also introduce a mechanism to combine images to construct what we call fractional probability regularization. Moreover, we present a fast way to calibrate the network after training. Finally, we propose a composite score to perform out-of-distribution detection. Our experiments show that DisMax usually outperforms current approaches simultaneously in classification accuracy, uncertainty estimation, and out-of-distribution detection while maintaining deterministic neural network inference efficiency. The code to reproduce the results is available.1 Copyright © 2022, The Authors. All rights reserved.

关键词： Efficiency

learning Domain Randomization Distributions for Training Robust Locomotion Policies

学校读者我要写书评

暂无评论

Learning Domain Randomization Distributions for Training Rob...

2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Melissa Mozian Juan Camilo Gamboa Higuera David Meger Gregory Dudek Montreal Institute of Learning Algorithms (MILA) and the Mobile Robotics Lab (MRL) at the School of Computer Science McGill University Montreal Canada

ISBN: (数字)9781728162126

ISBN: (纸本)9781728162133

This paper considers the problem of learning behaviors in simulation without knowledge of the precise dynamical properties of the target robot platform(s). In this context, our learning goal is to mutually maximize task efficacy on each environment considered and generalization across the widest possible range of environmental conditions. The physical parameters of the simulator are modified by a component of our technique that learns the Domain Randomization (DR) that is appropriate at each learning epoch to maximally challenge the current behavior policy, without being overly challenging, which can hinder learning progress. This so-called sweet spot distribution is a selection of simulated domains with the following properties: 1) The trained policy should be successful in environments sampled from the domain randomization distribution; and 2) The DR distribution made as wide as possible, to increase variability in the environments. These properties aim to ensure the trajectories encountered in the target system are close to those observed during training, as existing methods in machine learning are better suited for interpolation than extrapolation. We show how adapting the DR distribution while training context-conditioned policies results in improvements on jump-start and asymptotic performance when transferring a learned policy to the target environment 1 .

关键词： Training Interpolation Extrapolation Machine learning Trajectory Task analysis Intelligent robots

Record and Reward Federated learning Contributions with Blockchain

学校读者我要写书评

暂无评论

Record and Reward Federated Learning Contributions with Bloc...

International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery, CyberC

作者： Ismael Martinez Sreya Francis Abdelhakim Senhaji Hafid Department of Computer Science and Operations Research University of Montreal Montreal Canada Montreal Institute of Learning Algorithms University of Montreal Montreal Canada University of Montreal Montreal QC Canada

Although Federated learning allows for participants to contribute their local data without it being revealed, it faces issues in data security and in accurately paying participants for quality data contributions. In this paper, we propose an EOS Blockchain design and workflow to establish data security, a novel validation error based metric upon which we qualify gradient uploads for payment, and implement a small example of our blockchain Federated learning model to analyze its performance.

关键词： Training Blockchain Data models Smart contracts Earth Observing System Machine learning Distributed databases