Denis Thérien
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Denis Thérien has a total of 50 co-authors. Here are the top co-authors by number of shared publications:
Pascal Tesson
Département d'Informatique et de Génie Logiciel, Université Laval, Pavilion Adrien-Pouliot, Université Laval (Québec), Canada and McGill University
2 shared publications- Timothy P. Lillicrap
Google DeepMind, London, United Kingdom
2 shared publications - Adam Kepecs
Department of Neuroscience and Department of Psychiatry, Washington University in St. Louis, St. Louis, MO, USA
1 shared publication Amelia Christensen
Department of Electrical Engineering, Stanford University, Stanford, CA, USA
1 shared publication- Ana Marasović
University of Utah, Salt Lake City, USA
1 shared publication Andrew Saxe
Department of Experimental Psychology, University of Oxford, Oxford, UK
1 shared publication
Latest Publications
- Open Access
- 25 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 4491-4510
Societal Frameworks Can Improve LLM Alignment
- 25 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 4491-4510
Open AccessSocietal Frameworks Can Improve LLM Alignment
- Top Cited Papers
- 28 October 2019
- Published by Springer Nature in Nature Neuroscience
- Vol. 22 (11) , 1761-1770
A deep learning framework for neuroscience
Systems neuroscience seeks explanations for how the brain implements a wide variety of perceptual, cognitive and motor tasks. Conversely, artificial intelligence attempts to design computational systems based on the tasks they will have to solve. In artificial neural networks, the three components specified by design are the objective functions, the learning rules and the architectures. With the growing success of deep learning, which utilizes brain-inspired architectures, these three designed components have increasingly become central to how we model, engineer and optimize complex artificial learning systems. Here we argue that a greater focus on these components would also benefit systems neuroscience. We give examples of how this optimization-based framework can drive theoretical and experimental progress in neuroscience. We contend that this principled perspective on systems neuroscience will help to generate more rapid progress.
- 28 October 2019
- Published by Springer Nature in Nature Neuroscience
- Vol. 22 (11) , 1761-1770
Top Cited PapersA deep learning framework for neuroscience
Systems neuroscience seeks explanations for how the brain implements a wide variety of perceptual, cognitive and motor tasks. Conversely, artificial intelligence attempts to design computational systems based on the tasks they will have to solve. In artificial neural networks, the three components specified by design are the objective functions, the learning rules and the architectures. With the growing success of deep learning, which utilizes brain-inspired architectures, these three designed components have increasingly become central to how we model, engineer and optimize complex artificial learning systems. Here we argue that a greater focus on these components would also benefit systems neuroscience. We give examples of how this optimization-based framework can drive theoretical and experimental progress in neuroscience. We contend that this principled perspective on systems neuroscience will help to generate more rapid progress.
- 1 February 2006
- Published by Elsevier in Information and Computation
- Vol. 204 (2) , 177-209
Learning expressions and programs over monoids
- 1 February 2006
- Published by Elsevier in Information and Computation
- Vol. 204 (2) , 177-209
Learning expressions and programs over monoids
- 1 August 2005
- Published by World Scientific Pub Co Pte Ltd in International Journal of Foundations of Computer Science
- Vol. 16 (04) , 625-644
THE DOT-DEPTH AND THE POLYNOMIAL HIERARCHIES CORRESPOND ON THE DELTA LEVELS
It is well-known that the Σk- and Πk-levels of the dot-depth hierarchy and the polynomial hierarchy correspond via leaf languages. We extend this correspondence to the Δk-levels of these hierarchies: [Formula: see text]. The same methods are used to give evidence against an earlier conjecture of Straubing and Thérien about a leaf-language upper bound for BPP.
- 1 August 2005
- Published by World Scientific Pub Co Pte Ltd in International Journal of Foundations of Computer Science
- Vol. 16 (04) , 625-644
THE DOT-DEPTH AND THE POLYNOMIAL HIERARCHIES CORRESPOND ON THE DELTA LEVELS
It is well-known that the Σk- and Πk-levels of the dot-depth hierarchy and the polynomial hierarchy correspond via leaf languages. We extend this correspondence to the Δk-levels of these hierarchies: [Formula: see text]. The same methods are used to give evidence against an earlier conjecture of Straubing and Thérien about a leaf-language upper bound for BPP.
- 20 January 2003
- Published by Springer Nature in Theory of Computing Systems
- Vol. 36 (1) , 29-69
Regular Languages Defined by Generalized First-Order Formulas with a Bounded Number of Bound Variables
- 20 January 2003
- Published by Springer Nature in Theory of Computing Systems
- Vol. 36 (1) , 29-69
Regular Languages Defined by Generalized First-Order Formulas with a Bounded Number of Bound Variables