咨询与建议

限定检索结果

文献类型

  • 80 篇 期刊文献
  • 36 篇 会议
  • 3 册 图书

馆藏范围

  • 119 篇 电子文献
  • 0 种 纸本馆藏

日期分布

学科分类号

  • 86 篇 工学
    • 55 篇 计算机科学与技术...
    • 52 篇 软件工程
    • 32 篇 生物工程
    • 16 篇 信息与通信工程
    • 13 篇 生物医学工程(可授...
    • 9 篇 光学工程
    • 7 篇 化学工程与技术
    • 3 篇 机械工程
    • 3 篇 电气工程
    • 3 篇 电子科学与技术(可...
    • 3 篇 控制科学与工程
    • 2 篇 材料科学与工程(可...
    • 2 篇 土木工程
    • 2 篇 环境科学与工程(可...
    • 2 篇 安全科学与工程
  • 58 篇 理学
    • 32 篇 生物学
    • 29 篇 数学
    • 13 篇 统计学(可授理学、...
    • 11 篇 物理学
    • 8 篇 化学
    • 2 篇 大气科学
    • 2 篇 地球物理学
  • 16 篇 管理学
    • 10 篇 图书情报与档案管...
    • 8 篇 管理科学与工程(可...
    • 4 篇 工商管理
  • 10 篇 法学
    • 10 篇 社会学
  • 7 篇 医学
    • 7 篇 基础医学(可授医学...
    • 7 篇 临床医学
    • 7 篇 药学(可授医学、理...
  • 1 篇 哲学
    • 1 篇 哲学
  • 1 篇 教育学
  • 1 篇 文学

主题

  • 8 篇 generative adver...
  • 8 篇 machine learning
  • 7 篇 convolution
  • 6 篇 deep learning
  • 5 篇 task analysis
  • 4 篇 deep neural netw...
  • 4 篇 computer archite...
  • 4 篇 image segmentati...
  • 4 篇 training
  • 3 篇 visualization
  • 3 篇 semantics
  • 3 篇 forecasting
  • 2 篇 knowledge based ...
  • 2 篇 reinforcement le...
  • 2 篇 magnetic resonan...
  • 2 篇 signal encoding
  • 2 篇 markov processes
  • 2 篇 graph neural net...
  • 2 篇 diagnosis
  • 2 篇 computational mo...

机构

  • 28 篇 montreal institu...
  • 9 篇 montreal institu...
  • 8 篇 montreal institu...
  • 8 篇 hec montreal
  • 7 篇 montreal institu...
  • 7 篇 montreal institu...
  • 7 篇 montreal institu...
  • 6 篇 cifar
  • 6 篇 montreal institu...
  • 5 篇 school of comput...
  • 5 篇 department of ch...
  • 5 篇 centro de inform...
  • 5 篇 department of ch...
  • 4 篇 centro de inform...
  • 4 篇 montreal institu...
  • 3 篇 harvard universi...
  • 3 篇 facebook ai rese...
  • 3 篇 microsoft resear...
  • 3 篇 department of co...
  • 3 篇 mila-quebec inst...

作者

  • 28 篇 bengio yoshua
  • 7 篇 pineau joelle
  • 7 篇 zanchettin clebe...
  • 7 篇 tang jian
  • 6 篇 macêdo david
  • 6 篇 david macêdo
  • 6 篇 cleber zanchetti...
  • 6 篇 cohen joseph pau...
  • 5 篇 zhang saizheng
  • 4 篇 pal chris
  • 4 篇 subramanian sand...
  • 4 篇 sankar chinnadhu...
  • 4 篇 luck margaux
  • 4 篇 sordoni alessand...
  • 4 篇 romero adriana
  • 4 篇 yoshua bengio
  • 4 篇 serban iulian v.
  • 3 篇 gulcehre caglar
  • 3 篇 ke nan rosemary
  • 3 篇 adriano l. i. ol...

语言

  • 119 篇 英文
检索条件"机构=Montreal Institute for Learning Algorithms"
119 条 记 录,以下是91-100 订阅
Focused hierarchical RNNs for conditional sequence processing
arXiv
收藏 引用
arXiv 2018年
作者: Ke, Nan Rosemary Zolna, Konrad Sordoni, Alessandro Lin, Zhouhan Trischler, Adam Bengio, Yoshua Pineau, Joelle Charlin, Laurent Pal, Chris Montreal Institute for Learning Algorithms Montreal Canada Polytechnique Montreal MontréalQuébec Canada Microsoft Research Montreal Canada Jagiellonian University Cracow Poland AdeptMind Scholar University of Montreal MontréalQuébec Canada Senior Cifar Member McGill University MontréalQuébec Canada Facebook AI Research Montreal HEC Montreal Canada
Recurrent Neural Networks (RNNs) with attention mechanisms have obtained state-of-the-art results for many sequence processing tasks. Most of these models use a simple form of encoder with attention that looks over th... 详细信息
来源: 评论
MovieGraphs: Towards understanding human-centric situations from videos
arXiv
收藏 引用
arXiv 2017年
作者: Vicol, Paul Tapaswi, Makarand Castrejón, Lluís Fidler, Sanja University of Toronto Vector Institute Montreal Institute for Learning Algorithms
There is growing interest in artificial intelligence to build socially intelligent robots. This requires machines to have the ability to "read" people's emotions, motivations, and other factors that affe... 详细信息
来源: 评论
Image segmentation by iterative inference from conditional score estimation
arXiv
收藏 引用
arXiv 2017年
作者: Romero, Adriana Drozdzal, Michal Erraqabi, Akram Jégou, Simon Bengio, Yoshua Montreal Institute for Learning Algorithms MontrealQC Canada Imagia Cybernetics MontrealQC Canada
Inspired by the combination of feedforward and iterative computations in the visual cortex, and taking advantage of the ability of denoising autoencoders to estimate the score of a joint distribution, we propose a nov... 详细信息
来源: 评论
Plug and play generative networks: Conditional iterative generation of images in latent space  30
Plug and play generative networks: Conditional iterative gen...
收藏 引用
30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017
作者: Nguyen, Anh Clune, Jeff Bengio, Yoshua Dosovitskiy, Alexey Yosinski, Jason University of Wyoming United States Uber AI Labs University of Wyoming United States Montreal Institute for Learning Algorithms Canada University of Freiburg Germany Uber AI Labs Canada
Generating high-resolution, photo-realistic images has been a long-standing goal in machine learning. Recently, Nguyen et al. [37] showed one interesting way to synthesize novel images by performing gradient ascent in... 详细信息
来源: 评论
Improved training of wasserstein GANs
arXiv
收藏 引用
arXiv 2017年
作者: Gulrajani, Ishaan Ahmed, Faruk Arjovsky, Martin Dumoulin, Vincent Courville, Aaron Montreal Institute for Learning Algorithms Courant Institute of Mathematical Sciences CIFAR Google Brain
Generative Adversarial Networks (GANs) are powerful generative models, but suffer from training instability. The recently proposed Wasserstein GAN (WGAN) makes progress toward stable training of GANs, but sometimes ca... 详细信息
来源: 评论
Machine comprehension by text-to-text neural question generation
arXiv
收藏 引用
arXiv 2017年
作者: Yuan, Xingdi Wang, Tong Gulcehre, Caglar Sordoni, Alessandro Bachman, Philip Subramanian, Sandeep Zhang, Saizheng Trischler, Adam Microsoft Maluuba Montreal Institute for Learning Algorithms Université de Montréal
We propose a recurrent neural model that generates natural-language questions from documents, conditioned on answers. We show how to train the model using a combination of supervised and reinforcement learning. After ... 详细信息
来源: 评论
*** - Reproducing intuition
arXiv
收藏 引用
arXiv 2017年
作者: Cohen, Joseph Paul Lo, Henry Z. Institute for Reproducible Research Montreal Institute for Learning Algorithms Université of Montréal Institute for Reproducible Research
We present ***, a platform for post-publication discussion of research papers. On ***, the research community can read and write summaries of papers in order to increase accessible and reproducibility. Summaries conta... 详细信息
来源: 评论
Multi-Region bilinear convolutional neural networks for person re-identification
Multi-Region bilinear convolutional neural networks for pers...
收藏 引用
IEEE Conference on Advanced Video and Signal Based Surveillance (AVSS)
作者: Evgeniya Ustinova Yaroslav Ganin Victor Lempitsky Skolkovo Institute of Science and Technology Moscow Skolkovo Institute of Science and Technology Moscow Montreal Institute for Learning Algorithms Montreal Quebec
In this work we propose a new architecture for person re-identification. As the task of re-identification is inherently associated with embedding learning and non-rigid appearance description, our architecture is base... 详细信息
来源: 评论
A deep reinforcement learning chatbot
arXiv
收藏 引用
arXiv 2017年
作者: Serban, Iulian V. Sankar, Chinnadhurai Germain, Mathieu Zhang, Saizheng Lin, Zhouhan Subramanian, Sandeep Kim, Taesup Pieper, Michael Chandar, Sarath Ke, Nan Rosemary Rajeshwar, Sai de Brebisson, Alexandre Sotelo, Jose M.R. Suhubdy, Dendi Michalski, Vincent Nguyen, Alexandre Pineau, Joelle Bengio, Yoshua Montreal Institute for Learning Algorithms MontrealQC Canada School of Computer Science McGill University CIFAR
We present MILABOT: a deep reinforcement learning chatbot developed by the montreal institute for learning algorithms (MILA) for the Amazon Alexa Prize competition. MILABOT is capable of conversing with humans on popu... 详细信息
来源: 评论
On random weights for texture generation in one layer CNNS
On random weights for texture generation in one layer CNNS
收藏 引用
IEEE International Conference on Acoustics, Speech and Signal Processing
作者: Mihir Mongia Kundan Kumar Akram Erraqabi Yoshua Bengio Stanford University United States of America IIT Kanpur India Montreal Institute for Learning Algorithms Canada
Recent work in the literature has shown experimentally that one can use the lower layers of a trained convolutional neural network (CNN) to model natural textures. More interestingly, it has also been experimentally s... 详细信息
来源: 评论