1 code implementation • 31 May 2024 • Samuel Duffield, Kaelan Donatella, Johnathan Chiu, Phoebe Klett, Daniel Simpson
Although theoretically compelling, Bayesian learning with modern machine learning models is computationally challenging since it requires approximating a high dimensional posterior distribution.
1 code implementation • 22 May 2024 • Kaelan Donatella, Samuel Duffield, Maxwell Aifer, Denis Melanson, Gavin Crooks, Patrick J. Coles
Second-order training methods have better convergence properties than gradient descent but are rarely used in practice for large-scale training due to their computational overhead.
no code implementations • 8 Dec 2023 • Denis Melanson, Mohammad Abu Khater, Maxwell Aifer, Kaelan Donatella, Max Hunter Gordon, Thomas Ahle, Gavin Crooks, Antonio J. Martinez, Faris Sbahi, Patrick J. Coles
Recent breakthroughs in artificial intelligence (AI) algorithms have highlighted the need for novel computing hardware in order to truly unlock the potential for AI.
no code implementations • 8 Nov 2023 • Johnathan Chiu, Samuel Duffield, Max Hunter-Gordon, Kaelan Donatella, Max Aifer, Andi Gu
We introduce a novel approach to video modeling that leverages controlled differential equations (CDEs) to address key challenges in video tasks, notably video interpolation and mask propagation.
no code implementations • 9 Feb 2023 • Patrick J. Coles, Collin Szczepanski, Denis Melanson, Kaelan Donatella, Antonio J. Martinez, Faris Sbahi
Hence, we propose a novel computing paradigm, where software and hardware become inseparable.
no code implementations • 8 Feb 2021 • Kaelan Donatella, Zakari Denis, Alexandre Le Boité, Cristiano Ciuti
We investigate the continuous-time dynamics of highly-entangling intermediate-scale quantum circuits in the presence of dissipation and decoherence.
Quantum Physics