Zobrazeno 1 - 10
of 32
pro vyhledávání: '"Michalski, Vincent"'
Autor:
Rahman, Aamer Abdul, Agarwal, Pranav, Noumeir, Rita, Jouvet, Philippe, Michalski, Vincent, Kahou, Samira Ebrahimi
Offline reinforcement learning has shown promise for solving tasks in safety-critical settings, such as clinical decision support. Its application, however, has been limited by the lack of interpretability and interactivity for clinicians. To address
Externí odkaz:
http://arxiv.org/abs/2407.19380
Autor:
Armengol-Estapé, Jordi, Michalski, Vincent, Kumar, Ramnath, St-Charles, Pierre-Luc, Precup, Doina, Kahou, Samira Ebrahimi
Few-shot learning aims to learn representations that can tackle novel tasks given a small number of examples. Recent studies show that cross-modal learning can improve representations for few-shot classification. More specifically, language is a rich
Externí odkaz:
http://arxiv.org/abs/2405.18751
Autor:
Jain, Arnav Kumar, Sujit, Shivakanth, Joshi, Shruti, Michalski, Vincent, Hafner, Danijar, Ebrahimi-Kahou, Samira
Learning world models from their sensory inputs enables agents to plan for actions by imagining their future outcomes. World models have previously been shown to improve sample-efficiency in simulated environments with few objects, but have not yet b
Externí odkaz:
http://arxiv.org/abs/2210.11698
Autor:
Bouthillier, Xavier, Delaunay, Pierre, Bronzi, Mirko, Trofimov, Assya, Nichyporuk, Brennan, Szeto, Justin, Sepah, Naz, Raff, Edward, Madan, Kanika, Voleti, Vikram, Kahou, Samira Ebrahimi, Michalski, Vincent, Serdyuk, Dmitriy, Arbel, Tal, Pal, Chris, Varoquaux, Gaël, Vincent, Pascal
Strong empirical evidence that one machine-learning algorithm A outperforms another one B ideally calls for multiple trials optimizing the learning pipeline over sources of variation such as data sampling, data augmentation, parameter initialization,
Externí odkaz:
http://arxiv.org/abs/2103.03098
Autor:
Deudon, Michel, Kalaitzis, Alfredo, Goytom, Israel, Arefin, Md Rifat, Lin, Zhichao, Sankaran, Kris, Michalski, Vincent, Kahou, Samira E., Cornebise, Julien, Bengio, Yoshua
Generative deep learning has sparked a new wave of Super-Resolution (SR) algorithms that enhance single images with impressive aesthetic results, albeit with imaginary details. Multi-frame Super-Resolution (MFSR) offers a more grounded approach to th
Externí odkaz:
http://arxiv.org/abs/2002.06460
Autor:
Michalski, Vincent, Voleti, Vikram, Kahou, Samira Ebrahimi, Ortiz, Anthony, Vincent, Pascal, Pal, Chris, Precup, Doina
Batch normalization has been widely used to improve optimization in deep neural networks. While the uncertainty in batch statistics can act as a regularizer, using these dataset statistics specific to the training set impairs generalization in certai
Externí odkaz:
http://arxiv.org/abs/1908.00061
There has been growing interest in using neural networks and deep learning techniques to create dialogue systems. Conversational recommendation is an interesting setting for the scientific exploration of dialogue with natural language as the associat
Externí odkaz:
http://arxiv.org/abs/1812.07617
Synthesizing realistic images from text descriptions on a dataset like Microsoft Common Objects in Context (MS COCO), where each image can contain several objects, is a challenging task. Prior work has used text captions to generate images. However,
Externí odkaz:
http://arxiv.org/abs/1802.08216
Autor:
Serban, Iulian V., Sankar, Chinnadhurai, Germain, Mathieu, Zhang, Saizheng, Lin, Zhouhan, Subramanian, Sandeep, Kim, Taesup, Pieper, Michael, Chandar, Sarath, Ke, Nan Rosemary, Rajeswar, Sai, de Brebisson, Alexandre, Sotelo, Jose M. R., Suhubdy, Dendi, Michalski, Vincent, Nguyen, Alexandre, Pineau, Joelle, Bengio, Yoshua
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 popular small talk topics through bot
Externí odkaz:
http://arxiv.org/abs/1801.06700
Autor:
Kahou, Samira Ebrahimi, Michalski, Vincent, Atkinson, Adam, Kadar, Akos, Trischler, Adam, Bengio, Yoshua
We introduce FigureQA, a visual reasoning corpus of over one million question-answer pairs grounded in over 100,000 images. The images are synthetic, scientific-style figures from five classes: line plots, dot-line plots, vertical and horizontal bar
Externí odkaz:
http://arxiv.org/abs/1710.07300