Results 31 to 40 of about 201,672 (216)
A free-energy principle for representation learning [PDF]
Machine Learning: Science and Technology, 2021 Abstract This paper employs a formal connection of machine learning with thermodynamics to characterize the quality of learned representations for transfer learning. We discuss how information-theoretic functionals such as rate, distortion and classification loss of a model lie on a convex, so-called, equilibrium surface.
Yansong Gao, Pratik Chaudhari
openaire +3 more sources
A free energy principle for the brain [PDF]
Journal of Physiology-Paris, 2006 By formulating Helmholtz's ideas about perception, in terms of modern-day theories, one arrives at a model of perceptual inference and learning that can explain a remarkable range of neurobiological facts: using constructs from statistical physics, the problems of inferring the causes of sensory input and learning the causal structure of their ...
Karl, Friston +2 more
openaire +3 more sources
Application of the Free Energy Principle to Estimation and Control [PDF]
IEEE Transactions on Signal Processing, 2021 Based on a generative model (GM) and beliefs over hidden states, the free energy principle (FEP) enables an agent to sense and act by minimizing a free energy bound on Bayesian surprise. Inclusion of prior beliefs in the GM about desired states leads to active inference (ActInf).
Thijs van de Laar +2 more
openaire +3 more sources
The free energy principle induces neuromorphic development
Neuromorphic Computing and Engineering, 2022 Abstract We show how any finite physical system with morphological, i.e. three-dimensional embedding or shape, degrees of freedom and locally limited free energy will, under the constraints of the free energy principle, evolve over time towards a neuromorphic morphology that supports hierarchical computations in which each ‘level’ of the
Chris Fields 0001 +4 more
openaire +3 more sources
How Not to Argue about the Compatibility of Predictive Processing and 4E Cognition [PDF]
Organon F, 2021 In theories of cognition, 4E approaches to cognition are seen to refrain from employing robust representations in contrast to Predictive Process, where such posits are utilized extensively.
Yavuz Recep Başoğlu
doaj +1 more source
Reinforced Imitation Learning by Free Energy Principle
CoRR, 2021 Reinforcement Learning (RL) requires a large amount of exploration especially in sparse-reward settings. Imitation Learning (IL) can learn from expert demonstrations without exploration, but it never exceeds the expert's performance and is also vulnerable to distributional shift between demonstration and execution.
Ryoya Ogishima +2 more
openaire +2 more sources
Natural language syntax complies with the free-energy principle. [PDF]
Synthese, 2021 Natural language syntax yields an unbounded array of hierarchically structured expressions. We claim that these are used in the service of active inference in accord with the free-energy principle (FEP). While conceptual advances alongside modelling and simulation work have attempted to connect speech segmentation and linguistic communication with the ...
Murphy E, Holmes E, Friston K.
europepmc +6 more sources
Philosophies, 2021 A weak version of the life-mind continuity thesis entails that every living system also has a basic mind (with a non-representational form of intentionality).
Wanja Wiese, Karl J. Friston
doaj +1 more source
The Energy Homeostasis Principle: A Naturalistic Approach to Explain the Emergence of Behavior
Frontiers in Systems Neuroscience, 2022 It is still elusive to explain the emergence of behavior and understanding based on its neural mechanisms. One renowned proposal is the Free Energy Principle (FEP), which uses an information-theoretic framework derived from thermodynamic considerations ...
Sergio Vicencio-Jimenez +3 more
doaj +1 more source
Stochastic surprisal: An inferential measurement of free energy in neural networks
Frontiers in Neuroscience, 2023 This paper conjectures and validates a framework that allows for action during inference in supervised neural networks. Supervised neural networks are constructed with the objective to maximize their performance metric in any given task.
Mohit Prabhushankar, Ghassan AlRegib
doaj +1 more source