Zobrazeno 1 - 10
of 461
pro vyhledávání: '"Alain Guillaume"'
Autor:
Delaunay, Pierre, Bouthillier, Xavier, Breuleux, Olivier, Ortiz-Gagné, Satya, Bilaniuk, Olexa, Normandin, Fabrice, Bergeron, Arnaud, Carrez, Bruno, Alain, Guillaume, Blanc, Soline, Osterrath, Frédéric, Viviano, Joseph, Patil, Roger Creus-Castanyer Darshan, Awal, Rabiul, Zhang, Le
AI workloads, particularly those driven by deep learning, are introducing novel usage patterns to high-performance computing (HPC) systems that are not comprehensively captured by standard HPC benchmarks. As one of the largest academic research cente
Externí odkaz:
http://arxiv.org/abs/2411.11940
DeepDrummer is a drum loop generation tool that uses active learning to learn the preferences (or current artistic intentions) of a human user from a small number of interactions. The principal goal of this tool is to enable an efficient exploration
Externí odkaz:
http://arxiv.org/abs/2008.04391
Recently, the Deep Planning Network (PlaNet) approach was introduced as a model-based reinforcement learning method that learns environment dynamics directly from pixel observations. This architecture is useful for learning tasks in which either the
Externí odkaz:
http://arxiv.org/abs/1911.03594
The loss function of deep networks is known to be non-convex but the precise nature of this nonconvexity is still an active area of research. In this work, we study the loss landscape of deep networks through the eigendecompositions of their Hessian
Externí odkaz:
http://arxiv.org/abs/1902.02366
Autor:
Romain Chaumillon, Nadia Alahyane, Patrice Senot, Christelle Lemoine-Lardennois, Karine Doré-Mazars, Dorine Vergilino-Perez, Alain Guillaume
Publikováno v:
Scientific Reports, Vol 12, Iss 1, Pp 1-14 (2022)
Abstract The functional consequences of the visual system lateralization referred to as “eye dominance” remain poorly understood. We previously reported shorter hand reaction times for targets appearing in the contralateral visual hemifield with
Externí odkaz:
https://doaj.org/article/28cb2d4f901b48418c664f7921673351
Autor:
Alain, Guillaume, Bengio, Yoshua
Neural network models have a reputation for being black boxes. We propose to monitor the features at every layer of a model and measure how suitable they are for classification. We use linear classifiers, which we refer to as "probes", trained entire
Externí odkaz:
http://arxiv.org/abs/1610.01644
Autor:
The Theano Development Team, Al-Rfou, Rami, Alain, Guillaume, Almahairi, Amjad, Angermueller, Christof, Bahdanau, Dzmitry, Ballas, Nicolas, Bastien, Frédéric, Bayer, Justin, Belikov, Anatoly, Belopolsky, Alexander, Bengio, Yoshua, Bergeron, Arnaud, Bergstra, James, Bisson, Valentin, Snyder, Josh Bleecher, Bouchard, Nicolas, Boulanger-Lewandowski, Nicolas, Bouthillier, Xavier, de Brébisson, Alexandre, Breuleux, Olivier, Carrier, Pierre-Luc, Cho, Kyunghyun, Chorowski, Jan, Christiano, Paul, Cooijmans, Tim, Côté, Marc-Alexandre, Côté, Myriam, Courville, Aaron, Dauphin, Yann N., Delalleau, Olivier, Demouth, Julien, Desjardins, Guillaume, Dieleman, Sander, Dinh, Laurent, Ducoffe, Mélanie, Dumoulin, Vincent, Kahou, Samira Ebrahimi, Erhan, Dumitru, Fan, Ziye, Firat, Orhan, Germain, Mathieu, Glorot, Xavier, Goodfellow, Ian, Graham, Matt, Gulcehre, Caglar, Hamel, Philippe, Harlouchet, Iban, Heng, Jean-Philippe, Hidasi, Balázs, Honari, Sina, Jain, Arjun, Jean, Sébastien, Jia, Kai, Korobov, Mikhail, Kulkarni, Vivek, Lamb, Alex, Lamblin, Pascal, Larsen, Eric, Laurent, César, Lee, Sean, Lefrancois, Simon, Lemieux, Simon, Léonard, Nicholas, Lin, Zhouhan, Livezey, Jesse A., Lorenz, Cory, Lowin, Jeremiah, Ma, Qianli, Manzagol, Pierre-Antoine, Mastropietro, Olivier, McGibbon, Robert T., Memisevic, Roland, van Merriënboer, Bart, Michalski, Vincent, Mirza, Mehdi, Orlandi, Alberto, Pal, Christopher, Pascanu, Razvan, Pezeshki, Mohammad, Raffel, Colin, Renshaw, Daniel, Rocklin, Matthew, Romero, Adriana, Roth, Markus, Sadowski, Peter, Salvatier, John, Savard, François, Schlüter, Jan, Schulman, John, Schwartz, Gabriel, Serban, Iulian Vlad, Serdyuk, Dmitriy, Shabanian, Samira, Simon, Étienne, Spieckermann, Sigurd, Subramanyam, S. Ramana, Sygnowski, Jakub, Tanguay, Jérémie, van Tulder, Gijs, Turian, Joseph, Urban, Sebastian, Vincent, Pascal, Visin, Francesco, de Vries, Harm, Warde-Farley, David, Webb, Dustin J., Willson, Matthew, Xu, Kelvin, Xue, Lijun, Yao, Li, Zhang, Saizheng, Zhang, Ying
Theano is a Python library that allows to define, optimize, and evaluate mathematical expressions involving multi-dimensional arrays efficiently. Since its introduction, it has been one of the most used CPU and GPU mathematical compilers - especially
Externí odkaz:
http://arxiv.org/abs/1605.02688
Humans are able to accelerate their learning by selecting training materials that are the most informative and at the appropriate level of difficulty. We propose a framework for distributing deep learning in which one set of workers search for the mo
Externí odkaz:
http://arxiv.org/abs/1511.06481
Autor:
Alain, Guillaume, Bengio, Yoshua, Yao, Li, Yosinski, Jason, Thibodeau-Laufer, Eric, Zhang, Saizheng, Vincent, Pascal
We introduce a novel training principle for probabilistic models that is an alternative to maximum likelihood. The proposed Generative Stochastic Networks (GSN) framework is based on learning the transition operator of a Markov chain whose stationary
Externí odkaz:
http://arxiv.org/abs/1503.05571
Stochastic binary hidden units in a multi-layer perceptron (MLP) network give at least three potential benefits when compared to deterministic MLP networks. (1) They allow to learn one-to-many type of mappings. (2) They can be used in structured pred
Externí odkaz:
http://arxiv.org/abs/1406.2989