Search Results for author: Roland Memisevic

Found 20 papers, 8 papers with code

On the effectiveness of task granularity for transfer learning

1 code implementation24 Apr 2018 Farzaneh Mahdisoltani, Guillaume Berger, Waseem Gharbieh, David Fleet, Roland Memisevic

We describe a DNN for video classification and captioning, trained end-to-end, with shared features, to solve tasks at different levels of granularity, exploring the link between granularity in a source task and the quality of learned features for transfer learning.

Classification General Classification +2

Theano: A Python framework for fast computation of mathematical expressions

1 code implementation9 May 2016 The Theano Development Team, Rami Al-Rfou, Guillaume Alain, Amjad Almahairi, Christof Angermueller, Dzmitry Bahdanau, Nicolas Ballas, Frédéric Bastien, Justin Bayer, Anatoly Belikov, Alexander Belopolsky, Yoshua Bengio, Arnaud Bergeron, James Bergstra, Valentin Bisson, Josh Bleecher Snyder, Nicolas Bouchard, Nicolas Boulanger-Lewandowski, Xavier Bouthillier, Alexandre de Brébisson, Olivier Breuleux, Pierre-Luc Carrier, Kyunghyun Cho, Jan Chorowski, Paul Christiano, Tim Cooijmans, Marc-Alexandre Côté, Myriam Côté, Aaron Courville, Yann N. Dauphin, Olivier Delalleau, Julien Demouth, Guillaume Desjardins, Sander Dieleman, Laurent Dinh, Mélanie Ducoffe, Vincent Dumoulin, Samira Ebrahimi Kahou, Dumitru Erhan, Ziye Fan, Orhan Firat, Mathieu Germain, Xavier Glorot, Ian Goodfellow, Matt Graham, Caglar Gulcehre, Philippe Hamel, Iban Harlouchet, Jean-Philippe Heng, Balázs Hidasi, Sina Honari, Arjun Jain, Sébastien Jean, Kai Jia, Mikhail Korobov, Vivek Kulkarni, Alex Lamb, Pascal Lamblin, Eric Larsen, César Laurent, Sean Lee, Simon Lefrancois, Simon Lemieux, Nicholas Léonard, Zhouhan Lin, Jesse A. Livezey, Cory Lorenz, Jeremiah Lowin, Qianli Ma, Pierre-Antoine Manzagol, Olivier Mastropietro, Robert T. McGibbon, Roland Memisevic, Bart van Merriënboer, Vincent Michalski, Mehdi Mirza, Alberto Orlandi, Christopher Pal, Razvan Pascanu, Mohammad Pezeshki, Colin Raffel, Daniel Renshaw, Matthew Rocklin, Adriana Romero, Markus Roth, Peter Sadowski, John Salvatier, François Savard, Jan Schlüter, John Schulman, Gabriel Schwartz, Iulian Vlad Serban, Dmitriy Serdyuk, Samira Shabanian, Étienne Simon, Sigurd Spieckermann, S. Ramana Subramanyam, Jakub Sygnowski, Jérémie Tanguay, Gijs van Tulder, Joseph Turian, Sebastian Urban, Pascal Vincent, Francesco Visin, Harm de Vries, David Warde-Farley, Dustin J. Webb, Matthew Willson, Kelvin Xu, Lijun Xue, Li Yao, Saizheng Zhang, Ying Zhang

Since its introduction, it has been one of the most used CPU and GPU mathematical compilers - especially in the machine learning community - and has shown steady performance improvements.

Dimensionality Reduction General Classification

Generating images with recurrent adversarial networks

1 code implementation16 Feb 2016 Daniel Jiwoong Im, Chris Dongjoo Kim, Hui Jiang, Roland Memisevic

Gatys et al. (2015) showed that optimizing pixels to match features in a convolutional network with respect reference image features is a way to render images of high visual quality.

Regularizing RNNs by Stabilizing Activations

1 code implementation26 Nov 2015 David Krueger, Roland Memisevic

We stabilize the activations of Recurrent Neural Networks (RNNs) by penalizing the squared distance between successive hidden states' norms.

Language Modelling

Denoising Criterion for Variational Auto-Encoding Framework

no code implementations19 Nov 2015 Daniel Jiwoong Im, Sungjin Ahn, Roland Memisevic, Yoshua Bengio

Denoising autoencoders (DAE) are trained to reconstruct their clean inputs with noise injected at the input level, while variational autoencoders (VAE) are trained with noise injected in their stochastic hidden layer, with a regularizer that encourages this noise injection.

Denoising

RATM: Recurrent Attentive Tracking Model

no code implementations29 Oct 2015 Samira Ebrahimi Kahou, Vincent Michalski, Roland Memisevic

The proposed Recurrent Attentive Tracking Model performs well on all three tasks and can generalize to related but previously unseen sequences from a challenging tracking data set.

Frame Object Tracking

Dropout as data augmentation

no code implementations29 Jun 2015 Xavier Bouthillier, Kishore Konda, Pascal Vincent, Roland Memisevic

Dropout is typically interpreted as bagging a large number of models sharing parameters.

Data Augmentation

Conservativeness of untied auto-encoders

no code implementations25 Jun 2015 Daniel Jiwoong Im, Mohamed Ishmael Diwan Belghazi, Roland Memisevic

We discuss necessary and sufficient conditions for an auto-encoder to define a conservative vector field, in which case it is associated with an energy function akin to the unnormalized log-probability of the data.

Denoising

On Using Very Large Target Vocabulary for Neural Machine Translation

1 code implementation IJCNLP 2015 Sébastien Jean, Kyunghyun Cho, Roland Memisevic, Yoshua Bengio

The models trained by the proposed approach are empirically found to outperform the baseline models with a small vocabulary as well as the LSTM-based neural machine translation models.

Machine Translation Translation

Modeling Deep Temporal Dependencies with Recurrent Grammar Cells""

no code implementations NeurIPS 2014 Vincent Michalski, Roland Memisevic, Kishore Konda

We propose modeling time series by representing the transformations that take a frame at time t to a frame at time t+1.

Frame Time Series

Zero-bias autoencoders and the benefits of co-adapting features

no code implementations13 Feb 2014 Kishore Konda, Roland Memisevic, David Krueger

We show that negative biases are a natural result of using a hidden layer whose responsibility is to both represent the input data and act as a selection mechanism that ensures sparsity of the representation.

Modeling sequential data using higher-order relational features and predictive training

no code implementations10 Feb 2014 Vincent Michalski, Roland Memisevic, Kishore Konda

In this work we extend bi-linear models by introducing "higher-order mapping units" that allow us to encode transformations between frames and transformations between transformations.

Frame

Unsupervised learning of depth and motion

no code implementations12 Dec 2013 Kishore Konda, Roland Memisevic

We present a model for the joint estimation of disparity and motion.

Learning to encode motion using spatio-temporal synchrony

no code implementations13 Jun 2013 Kishore Reddy Konda, Roland Memisevic, Vincent Michalski

To this end, we show that the detection of spatial transformations can be viewed as the detection of synchrony between the image sequence and a sequence of features undergoing the motion we wish to detect.

Motion Estimation

Gated Softmax Classification

no code implementations NeurIPS 2010 Roland Memisevic, Christopher Zach, Marc Pollefeys, Geoffrey E. Hinton

We describe a log-bilinear" model that computes class probabilities by combining an input vector multiplicatively with a vector of binary latent variables.

Classification General Classification

Cannot find the paper you are looking for? You can Submit a new open access paper.