Search Results - "Elmoznino, Eric"

High-performing neural network models of visual cortex benefit from high latent dimensionality by Elmoznino, Eric, Bonner, Michael F

“…Geometric descriptions of deep neural networks (DNNs) have the potential to uncover core representational principles of computational models in neuroscience…”
Get full text

Latent dimensionality scales with the performance of deep learning models of visual cortex by Elmoznino, Eric, Bonner, Michael

Get full text

High-performing computational models of visual cortex are marked by high intrinsic dimensionality by Elmoznino, Eric, Bonner, Michael

Get full text

Toward a computational neuroscience of visual cortex without deep learning by Kazemian, Atlas, Elmoznino, Eric, Bonner, Michael

Get full text

Scene context is predictive of unconstrained object similarity judgments by Magri, Caterina, Elmoznino, Eric, Bonner, Michael F.

“…What makes objects alike in the human mind? Computational approaches for characterizing object similarity have largely focused on the visual forms of objects…”
Get full text

Sources of richness and ineffability for phenomenally conscious states by Ji, Xu, Elmoznino, Eric, Deane, George, Constant, Axel, Dumas, Guillaume, Lajoie, Guillaume, Simon, Jonathan, Bengio, Yoshua

“…Abstract Conscious states—state that there is something it is like to be in—seem both rich or full of detail and ineffable or hard to fully describe or recall…”
Get full text

A new procedure, free from human assessment that automatically grades some facial skin structural signs. Comparison with assessments by experts, using referential atlases of skin ageing by Jiang, Ruowei, Kezele, Irina, Levinshtein, Alex, Flament, Frederic, Zhang, Jingyi, Elmoznino, Eric, Ma, Junwei, Ma, He, Coquide, Jerome, Arcin, Vincent, Omoyuri, Esohe, Aarabi, Parham

“…Objective To develop an automatic system that grades the severity of facial signs through ‘selfies’ pictures taken by women of different ages and ethnics…”
Get full text

A Complexity-Based Theory of Compositionality by Elmoznino, Eric, Jiralerspong, Thomas, Bengio, Yoshua, Lajoie, Guillaume

“…Compositionality is believed to be fundamental to intelligence. In humans, it underlies the structure of thought, language, and higher-level reasoning. In AI,…”
Get full text

In-context learning and Occam's razor by Elmoznino, Eric, Marty, Tom, Kasetty, Tejas, Gagnon, Leo, Mittal, Sarthak, Fathi, Mahan, Sridhar, Dhanya, Lajoie, Guillaume

“…The goal of machine learning is generalization. While the No Free Lunch Theorem states that we cannot obtain theoretical guarantees for generalization without…”
Get full text

Does learning the right latent variables necessarily improve in-context learning? by Mittal, Sarthak, Elmoznino, Eric, Gagnon, Leo, Bhardwaj, Sangnie, Sridhar, Dhanya, Lajoie, Guillaume

“…Large autoregressive models like Transformers can solve tasks through in-context learning (ICL) without learning new weights, suggesting avenues for…”
Get full text

Amortizing intractable inference in large language models by Hu, Edward J, Jain, Moksh, Elmoznino, Eric, Kaddar, Younesse, Lajoie, Guillaume, Bengio, Yoshua, Malkin, Nikolay

“…Autoregressive large language models (LLMs) compress knowledge from their training data through next-token conditional distributions. This limits tractable…”
Get full text

Discrete, compositional, and symbolic representations through attractor dynamics by Nam, Andrew, Elmoznino, Eric, Malkin, Nikolay, McClelland, James, Bengio, Yoshua, Lajoie, Guillaume

“…Symbolic systems are powerful frameworks for modeling cognitive processes as they encapsulate the rules and relationships fundamental to many aspects of human…”
Get full text

Sources of Richness and Ineffability for Phenomenally Conscious States by Ji, Xu, Elmoznino, Eric, Deane, George, Constant, Axel, Dumas, Guillaume, Lajoie, Guillaume, Simon, Jonathan, Bengio, Yoshua

“…Conscious states (states that there is something it is like to be in) seem both rich or full of detail, and ineffable or hard to fully describe or recall. The…”
Get full text

Multi-agent cooperation through learning-aware policy gradients by Meulemans, Alexander, Kobayashi, Seijin, von Oswald, Johannes, Scherrer, Nino, Elmoznino, Eric, Richards, Blake, Lajoie, Guillaume, Arcas, Blaise Agüera y, Sacramento, João

“…Self-interested individuals often fail to cooperate, posing a fundamental challenge for multi-agent learning. How can we achieve cooperation among…”
Get full text

Consciousness in Artificial Intelligence: Insights from the Science of Consciousness by Butlin, Patrick, Long, Robert, Elmoznino, Eric, Bengio, Yoshua, Birch, Jonathan, Constant, Axel, Deane, George, Fleming, Stephen M, Frith, Chris, Ji, Xu, Kanai, Ryota, Klein, Colin, Lindsay, Grace, Michel, Matthias, Mudrik, Liad, Peters, Megan A. K, Schwitzgebel, Eric, Simon, Jonathan, VanRullen, Rufin

“…Whether current or near-term AI systems could be conscious is a topic of scientific interest and increasing public concern. This report argues for, and…”
Get full text