Zobrazeno 1 - 10
of 3 166
pro vyhledávání: '"BUCKLEY, CHRISTOPHER"'
Autor:
Innocenti, Francesco, Kinghorn, Paul, Yun-Farmbrough, Will, Varona, Miguel De Llanza, Singh, Ryan, Buckley, Christopher L.
We introduce JPC, a JAX library for training neural networks with Predictive Coding. JPC provides a simple, fast and flexible interface to train a variety of PC networks (PCNs) including discriminative, generative and hybrid models. Unlike existing l
Externí odkaz:
http://arxiv.org/abs/2412.03676
Autor:
Wei, Ran, Lee, Joseph, Wakayama, Shohei, Tschantz, Alexander, Heins, Conor, Buckley, Christopher, Carenbauer, John, Thiruvengada, Hari, Albarracin, Mahault, de Prado, Miguel, Horling, Petter, Winzell, Peter, Rajagopal, Renjith
Predicting future trajectories of nearby objects, especially under occlusion, is a crucial task in autonomous driving and safe robot navigation. Prior works typically neglect to maintain uncertainty about occluded objects and only predict trajectorie
Externí odkaz:
http://arxiv.org/abs/2410.10653
Recently, 3D Gaussian Splatting has emerged as a promising approach for modeling 3D scenes using mixtures of Gaussians. The predominant optimization method for these models relies on backpropagating gradients through a differentiable rendering pipeli
Externí odkaz:
http://arxiv.org/abs/2410.03592
Although research has produced promising results demonstrating the utility of active inference (AIF) in Markov decision processes (MDPs), there is relatively less work that builds AIF models in the context of environments and problems that take the f
Externí odkaz:
http://arxiv.org/abs/2409.14216
Publikováno v:
4th International Workshop on Active Inference, 2023
Organisms have to keep track of the information in the environment that is relevant for adaptive behaviour. Transmitting information in an economical and efficient way becomes crucial for limited-resourced agents living in high-dimensional environmen
Externí odkaz:
http://arxiv.org/abs/2409.08892
An open problem in artificial intelligence is how systems can flexibly learn discrete abstractions that are useful for solving inherently continuous problems. Previous work in computational neuroscience has considered this functional integration of d
Externí odkaz:
http://arxiv.org/abs/2409.01066
Autor:
Heins, Conor, Wu, Hao, Markovic, Dimitrije, Tschantz, Alexander, Beck, Jeff, Buckley, Christopher
Balancing computational efficiency with robust predictive performance is crucial in supervised learning, especially for critical applications. Standard deep learning models, while accurate and scalable, often lack probabilistic features like calibrat
Externí odkaz:
http://arxiv.org/abs/2408.16429
Predictive coding (PC) is an energy-based learning algorithm that performs iterative inference over network activities before updating weights. Recent work suggests that PC can converge in fewer learning steps than backpropagation thanks to its infer
Externí odkaz:
http://arxiv.org/abs/2408.11979
An open problem in artificial intelligence is how systems can flexibly learn discrete abstractions that are useful for solving inherently continuous problems. Previous work has demonstrated that a class of hybrid state-space model known as recurrent
Externí odkaz:
http://arxiv.org/abs/2408.10970
Autor:
Friston, Karl, Heins, Conor, Verbelen, Tim, Da Costa, Lancelot, Salvatori, Tommaso, Markovic, Dimitrije, Tschantz, Alexander, Koudahl, Magnus, Buckley, Christopher, Parr, Thomas
This paper describes a discrete state-space model -- and accompanying methods -- for generative modelling. This model generalises partially observed Markov decision processes to include paths as latent variables, rendering it suitable for active infe
Externí odkaz:
http://arxiv.org/abs/2407.20292