Search Results for author: Zafeirios Fountas

Found 13 papers, 1 papers with code

When in Doubt, Think Slow: Iterative Reasoning with Latent Imagination

no code implementations23 Feb 2024 Martin Benfeghoul, Umais Zahid, Qinghai Guo, Zafeirios Fountas

In an unfamiliar setting, a model-based reinforcement learning agent can be limited by the accuracy of its world model.

Model-based Reinforcement Learning

Sample as You Infer: Predictive Coding With Langevin Dynamics

no code implementations22 Nov 2023 Umais Zahid, Qinghai Guo, Zafeirios Fountas

We present a novel algorithm for parameter learning in generic deep generative models that builds upon the predictive coding (PC) framework of computational neuroscience.

Predictive Coding as a Neuromorphic Alternative to Backpropagation: A Critical Evaluation

no code implementations5 Apr 2023 Umais Zahid, Qinghai Guo, Zafeirios Fountas

Backpropagation has rapidly become the workhorse credit assignment algorithm for modern deep learning methods.

Curvature-Sensitive Predictive Coding with Approximate Laplace Monte Carlo

no code implementations9 Mar 2023 Umais Zahid, Qinghai Guo, Karl Friston, Zafeirios Fountas

In part, this has been due to the poor performance of models trained with PC when evaluated by both sample quality and marginal likelihood.

Long-horizon video prediction using a dynamic latent hierarchy

no code implementations29 Dec 2022 Alexey Zakharov, Qinghai Guo, Zafeirios Fountas

The task of video prediction and generation is known to be notoriously difficult, with the research in this area largely limited to short-term predictions.

Representation Learning Video Prediction

Modelling non-reinforced preferences using selective attention

no code implementations25 Jul 2022 Noor Sajid, Panagiotis Tigas, Zafeirios Fountas, Qinghai Guo, Alexey Zakharov, Lancelot Da Costa

These memories are selectively attended to, using attention and gating blocks, to update agent's preferences.

OpenAI Gym

Bayesian sense of time in biological and artificial brains

no code implementations14 Jan 2022 Zafeirios Fountas, Alexey Zakharov

Enquiries concerning the underlying mechanisms and the emergent properties of a biological brain have a long history of theoretical postulates and experimental findings.

Bayesian Inference

Exploration and preference satisfaction trade-off in reward-free learning

no code implementations ICML Workshop URL 2021 Noor Sajid, Panagiotis Tigas, Alexey Zakharov, Zafeirios Fountas, Karl Friston

In this paper, we pursue the notion that this learnt behaviour can be a consequence of reward-free preference learning that ensures an appropriate trade-off between exploration and preference satisfaction.

OpenAI Gym

Episodic Memory for Learning Subjective-Timescale Models

no code implementations3 Oct 2020 Alexey Zakharov, Matthew Crosby, Zafeirios Fountas

In model-based learning, an agent's model is commonly defined over transitions between consecutive states of an environment even though planning often requires reasoning over multi-step timescales, with intermediate states either unnecessary, or worse, accumulating prediction error.

Computational Efficiency

Deep active inference agents using Monte-Carlo methods

1 code implementation NeurIPS 2020 Zafeirios Fountas, Noor Sajid, Pedro A. M. Mediano, Karl Friston

In a more complex Animal-AI environment, our agents (using the same neural architecture) are able to simulate future state transitions and actions (i. e., plan), to evince reward-directed navigation - despite temporary suspension of visual input.

Multimodal Data Fusion based on the Global Workspace Theory

no code implementations26 Jan 2020 Cong Bao, Zafeirios Fountas, Temitayo Olugbade, Nadia Bianchi-Berthouze

We propose a novel neural network architecture, named the Global Workspace Network (GWN), which addresses the challenge of dynamic and unspecified uncertainties in multimodal data fusion.

Cannot find the paper you are looking for? You can Submit a new open access paper.