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
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
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
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
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
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
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
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
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 based on the deep bilinear convolutional network (Bilinear-CNN) that has been proposed recently for fine-grained classification of highly non-rigid objects. While the last stages of the original Bilinear-CNN architecture completely removes the geometric information from consideration by performing orderless pooling, we observe that a better embedding can be learned by performing bilinear pooling in a more local way, where each pooling is confined to a predefined region. Our architecture thus represents a compromise between traditional convolutional networks and bilinear CNNs and strikes a balance between rigid matching and completely ignoring spatial information. We perform the experimental validation of the new architecture on the three popular benchmark datasets (Market-1501, CUHK01, CUHK03), comparing it to baselines that include Bilinear-CNN as well as prior art. The new architecture outperforms the baseline on all three datasets, while performing better than state-of-the-art on two out of three. The code and the pretrained models of the approach will be made available at the time of publication.
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
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
ISBN:
(纸本)9781509041183
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 shown that only one layer with random filters can also model textures although with less variability. In this paper we ask the question as to why one layer CNNs with random filters are so effective in generating textures? We theoretically show that one layer convolutional architectures (without a non-linearity) paired with the an energy function used in previous literature, can in fact preserve and modulate frequency coefficients in a manner so that random weights and pretrained weights will generate the same type of images. Based on the results of this analysis we question whether similar properties hold in the case where one uses one convolution layer with a non-linearity. We show that in the case of ReLu non-linearity there are situations where only one input will give the minimum possible energy whereas in the case of no nonlinearity, there are always infinite solutions that will give the minimum possible energy. Thus we can show that in certain situations adding a ReLu non-linearity generates less variable images.
暂无评论