Search

Your search keyword '"Sajid, Noor"' showing total 7 results
Start Over Author "Sajid, Noor" Topic free energy principle
7 results on '"Sajid, Noor"'

1. Proceedings of the 2nd Applied Active Inference Symposium on 'Robotics', at the Active Inference Institute

Author

Friston, Karl, Schneider, Tim, Verbelen, Tim, White, Ben, Sajid, Noor, Chen, Wen-Hua, Lara, Bruno, Brown, Matt, Safron, Adam, Cloutier, JF, Smekal, Jakub, Knight, Bleu, and Friedman, Daniel

Subjects
Free Energy Principle, Active Inference, Robotics
Abstract

This is a transcript of the proceedings of the 2nd Applied Active Inference Symposium. There are twoSymposium sessions of four hours each, starting at 4 & 16 UTC on July 31st Watch link for 1st Symposium interval, July 31st at 4 UTC: https://youtu.be/zm2d9o5n0PU Watch link for 2nd Symposium interval, July 31st at 16 UTC: https://youtu.be/dTVHHenms_Y The Program is available at:https://coda.io/@active-inference-institute/2nd-applied-active-inference-symposium

Published
2022
Full Text
View/download PDF

2. On efficient computation in active inference.

Author

Paul, Aswin, Sajid, Noor, Da Costa, Lancelot, and Razi, Adeel

Subjects
*COST functions, *DYNAMIC programming, *COMPUTATIONAL complexity, *REINFORCEMENT learning, *ALGORITHMS
Abstract

Biological agents demonstrate a remarkable proficiency in calibrating appropriate scales of planning and evaluation when interacting with their environments. It follows logically that any decision-making algorithm aspiring to neurobiological plausibility must mirror these attributes, particularly regarding computational expenditure and the intricacy of evaluative processes. However, active inference encounters notable challenges in simulating apt behaviours within complex environments. These stem chiefly from its substantial computational demands and the intricate task of defining the agent's behaviour preference. We address these through a two-fold approach. First, we introduce a planning algorithm by using the Bellman-optimality principle to minimise the planning cost function (i.e., expected free energy). Briefly, we recursively compute the expected free energy of actions in reverse temporal sequence to significantly reduce the computational complexity. Secondly, inspired by the Z-learning algorithm, we propose a novel method to learn time-constrained agent preferences. We face-validate the efficacy of these through grid-world simulations and demonstrate precise model learning and planning, even under uncertainty. These algorithmic advances create new opportunities for various applications—in neuroscience and machine learning. • Introduced the Dynamic Programming Expected Free Energy (DPEFE) for efficient active inference planning. • Developed a new algorithm for learning time-constrained agent behaviour preferences. • Demonstrated, theoretically and via simulations, reduced computational cost by orders of magnitude. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

3. A Worked Example of the Bayesian Mechanics of Classical Objects

Author

Sakthivadivel, Dalton A. R., Filipe, Joaquim, Editorial Board Member, Ghosh, Ashish, Editorial Board Member, Prates, Raquel Oliveira, Editorial Board Member, Zhou, Lizhu, Editorial Board Member, Buckley, Christopher L., editor, Cialfi, Daniela, editor, Lanillos, Pablo, editor, Ramstead, Maxwell, editor, Sajid, Noor, editor, Shimazaki, Hideaki, editor, and Verbelen, Tim, editor

Published
2023
Full Text
View/download PDF

4. AIXI, FEP-AI, and Integrated World Models: Towards a Unified Understanding of Intelligence and Consciousness

Author

Safron, Adam, Filipe, Joaquim, Editorial Board Member, Ghosh, Ashish, Editorial Board Member, Prates, Raquel Oliveira, Editorial Board Member, Zhou, Lizhu, Editorial Board Member, Buckley, Christopher L., editor, Cialfi, Daniela, editor, Lanillos, Pablo, editor, Ramstead, Maxwell, editor, Sajid, Noor, editor, Shimazaki, Hideaki, editor, and Verbelen, Tim, editor

Published
2023
Full Text
View/download PDF

5. Home Run: Finding Your Way Home by Imagining Trajectories

Author

Tinguy, Daria de, Mazzaglia, Pietro, Verbelen, Tim, Dhoedt, Bart, Filipe, Joaquim, Editorial Board Member, Ghosh, Ashish, Editorial Board Member, Prates, Raquel Oliveira, Editorial Board Member, Zhou, Lizhu, Editorial Board Member, Buckley, Christopher L., editor, Cialfi, Daniela, editor, Lanillos, Pablo, editor, Ramstead, Maxwell, editor, Sajid, Noor, editor, Shimazaki, Hideaki, editor, and Verbelen, Tim, editor

Published
2023
Full Text
View/download PDF

6. Active inference on discrete state-spaces: A synthesis.

Author

Da Costa, Lancelot, Parr, Thomas, Sajid, Noor, Veselic, Sebastijan, Neacsu, Victorita, and Friston, Karl

Subjects
*FORECASTING, *DECISION making, *INTEROCEPTION, *SENSORY perception
Abstract

Active inference is a normative principle underwriting perception, action, planning, decision-making and learning in biological or artificial agents. From its inception, its associated process theory has grown to incorporate complex generative models, enabling simulation of a wide range of complex behaviours. Due to successive developments in active inference, it is often difficult to see how its underlying principle relates to process theories and practical implementation. In this paper, we try to bridge this gap by providing a complete mathematical synthesis of active inference on discrete state-space models. This technical summary provides an overview of the theory, derives neuronal dynamics from first principles and relates this dynamics to biological processes. Furthermore, this paper provides a fundamental building block needed to understand active inference for mixed generative models; allowing continuous sensations to inform discrete representations. This paper may be used as follows: to guide research towards outstanding challenges, a practical guide on how to implement active inference to simulate experimental behaviour, or a pointer towards various in-silico neurophysiological responses that may be used to make empirical predictions. • We review active inference on discrete state-spaces, a framework thought to underwrite perception, action, planning, decision-making and learning in biological and artificial agents. • We derive the associated process theory and discuss its biological plausibility. • We discuss outstanding challenges for the theory, its implementation and empirical validation. [ABSTRACT FROM AUTHOR]

Published
2020
Full Text
View/download PDF

7. Home Run: Finding Your Way Home by Imagining Trajectories

Author

Daria de Tinguy, Pietro Mazzaglia, Tim Verbelen, Bart Dhoedt, Buckley, Christopher L., Cialfi, Daniela, Lanillos, Pablo, Ramstead, Maxwell, Sajid, Noor, Shimazaki, Hideaki, and Verbelen, Tim

Subjects
FOS: Computer and information sciences, Computer Science - Machine Learning, Technology and Engineering, Artificial Intelligence (cs.AI), Computer Science - Artificial Intelligence, Free energy principle, Active inference, Robot navigation, Deep learning, Machine Learning (cs.LG)
Abstract

When studying unconstrained behaviour and allowing mice to leave their cage to navigate a complex labyrinth, the mice exhibit foraging behaviour in the labyrinth searching for rewards, returning to their home cage now and then, e.g. to drink. Surprisingly, when executing such a ``home run'', the mice do not follow the exact reverse path, in fact, the entry path and home path have very little overlap. Recent work proposed a hierarchical active inference model for navigation, where the low level model makes inferences about hidden states and poses that explain sensory inputs, whereas the high level model makes inferences about moving between locations, effectively building a map of the environment. However, using this ``map'' for planning, only allows the agent to find trajectories that it previously explored, far from the observed mice's behaviour. In this paper, we explore ways of incorporating before-unvisited paths in the planning algorithm, by using the low level generative model to imagine potential, yet undiscovered paths. We demonstrate a proof of concept in a grid-world environment, showing how an agent can accurately predict a new, shorter path in the map leading to its starting point, using a generative model learnt from pixel-based observations., Comment: accepted for International Workshop on Active Inference IWAI 2022, ECML PKDD workshop

Published
2022
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results