Search Results for author:
Found 38 papers, 6 papers with code
The graphical brain and deep inference
This presentation considers deep temporal models in the brain.
Robust Decision-Making Via Free Energy Minimization
Robustness towards these training/environment ambiguities is a core requirement for intelligent agents and its fulfillment is a long-standing challenge when deploying agents in the real world.
Brain in the Dark: Design Principles for Neuromimetic Inference under the Free Energy Principle
Deep learning has revolutionised artificial intelligence (AI) by enabling automatic feature extraction and function approximation from raw data.
SPM 25: open source neuroimaging analysis software
This paper reports the release of SPM 25. 01, a major new version of the software that incorporates novel analysis methods, optimisations of existing methods, as well as improved practices for open science and software development.
Possible principles for aligned structure learning agents
In brief, a possible path toward scalable aligned AI rests upon enabling artificial agents to learn a good model of the world that includes a good model of our preferences.
A Mathematical Perspective on Neurophenomenology
In summary, we formalise and characterise first-person subjective experience and its correspondence with third-person empirical measurements of brain and body, offering hypotheses for quantifying various aspects of phenomenology to be tested in future work.
From pixels to planning: scale-free active inference
This paper describes a discrete state-space model -- and accompanying methods -- for generative modelling.
Localising the Seizure Onset Zone from Single-Pulse Electrical Stimulation Responses with a CNN Transformer
Secondly, we demonstrate the efficacy of CNN Transformers with cross-channel attention in handling heterogeneous electrode placements, increasing the AUROC to 0. 730.
Mortal Computation: A Foundation for Biomimetic Intelligence
This review motivates and synthesizes research efforts in neuroscience-inspired artificial intelligence and biomimetic computing in terms of mortal computation.
Neural representation in active inference: using generative models to interact with -- and understand -- the lived world
This paper considers neural representation through the lens of active inference, a normative framework for understanding brain function.
Canonical Cortical Field Theories
Moreover, the neural field model was invariant, within a set of parameters, to the dynamical system used to model each neuronal mass.
Hierarchical generative modelling for autonomous robots
We approach this problem by hierarchical generative modelling equipped with multi-level planning-for autonomous task completion-that mimics the deep temporal architecture of human motor control.
A Survey on Brain-Inspired Deep Learning via Predictive Coding
Artificial intelligence (AI) is rapidly becoming one of the key technologies of this century.
Brain in the Dark: Design Principles for Neuro-mimetic Learning and Inference
Even though the brain operates in pure darkness, within the skull, it can infer the most likely causes of its sensory input.
Spectral Dynamic Causal Modelling: A Didactic Introduction and its Relationship with Functional Connectivity
We present a didactic introduction to spectral Dynamic Causal Modelling (DCM), a Bayesian state-space modelling approach used to infer effective connectivity from non-invasive neuroimaging data.
Designing explainable artificial intelligence with active inference: A framework for transparent introspection and decision-making
This paper investigates the prospect of developing human-interpretable, explainable artificial intelligence (AI) systems based on active inference and the free energy principle.
The inner screen model of consciousness: applying the free energy principle directly to the study of conscious experience
This paper presents a model of consciousness that follows directly from the free-energy principle (FEP).
Curvature-Sensitive Predictive Coding with Approximate Laplace Monte Carlo
In part, this has been due to the poor performance of models trained with PC when evaluated by both sample quality and marginal likelihood.
A variational synthesis of evolutionary and developmental dynamics
This paper introduces a variational formulation of natural selection, paying special attention to the nature of "things" and the way that different "kinds" of "things" are individuated from - and influence - each other.
Control flow in active inference systems
Living systems face both environmental complexity and limited access to free-energy resources.
Bistable perception, precision and neuromodulation
Bistable perception follows from observing a static, ambiguous, (visual) stimulus with two possible interpretations.
Natural Language Syntax Complies with the Free-Energy Principle
Natural language syntax yields an unbounded array of hierarchically structured expressions.
The Free Energy Principle drives neuromorphic development
We show how any system with morphological degrees of freedom and locally limited free energy will, under the constraints of the free energy principle, evolve toward a neuromorphic morphology that supports hierarchical computations in which each level of the hierarchy enacts a coarse-graining of its inputs, and dually a fine-graining of its outputs.
Global dynamics of neural mass models
Simulations evince a complex phase-space structure for these kinds of models; including stationary points and limit cycles and the possibility for bifurcations and transitions among different modes of activity.
Geometric Methods for Sampling, Optimisation, Inference and Adaptive Agents
In this chapter, we identify fundamental geometric structures that underlie the problems of sampling, optimisation, inference and adaptive decision-making.
pymdp: A Python library for active inference in discrete state spaces
Active inference is an account of cognition and behavior in complex systems which brings together action, perception, and learning under the theoretical mantle of Bayesian inference.
Insula Interoception, Active Inference and Feeling Representation
The body sends interoceptive visceral information through deep brain structures to the cerebral cortex.
Active inference, Bayesian optimal design, and expected utility
Conversely, active inference reduces to Bayesian decision theory in the absence of ambiguity and relative risk, i. e., expected utility maximization.
Bayesian brains and the Rényi divergence
Under the Bayesian brain hypothesis, behavioural variations can be attributed to different priors over generative model parameters.
Exploration and preference satisfaction trade-off in reward-free learning
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.
Active Inference Tree Search in Large POMDPs
Here, we introduce a novel method to plan in POMDPs--Active Inference Tree Search (AcT)--that combines the normative character and biological realism of a leading planning theory in neuroscience (Active Inference) and the scalability of tree search methods in AI.
Reward Maximisation through Discrete Active Inference
Precisely, we show the conditions under which active inference produces the optimal solution to the Bellman equation--a formulation that underlies several approaches to model-based reinforcement learning and control.
Action and Perception as Divergence Minimization
While the narrow objectives correspond to domain-specific rewards as typical in reinforcement learning, the general objectives maximize information with the environment through latent variable models of input sequences.
Sophisticated Inference
In this paper, we consider a sophisticated kind of active inference, using a recursive form of expected free energy.
Deep active inference agents using Monte-Carlo methods
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.
Neural dynamics under active inference: plausibility and efficiency of information processing
We then show that these neuronal dynamics approximate natural gradient descent, a well-known optimisation algorithm from information geometry that follows the steepest descent of the objective in information space.
Bayesian Belief Updating of Spatiotemporal Seizure Dynamics
Epileptic seizure activity shows complicated dynamics in both space and time.
Approximate Bayesian inference as a gauge theory
In a published paper [Sengupta, 2016], we have proposed that the brain (and other self-organized biological and artificial systems) can be characterized via the mathematical apparatus of a gauge theory.
