[go: up one dir, main page]

Champion et al., 2024 - Google Patents

Reframing the expected free energy: Four formulations and a unification

Champion et al., 2024

View PDF
Document ID
148890352098755265
Author
Champion T
Bowman H
Marković D
Grześ M
Publication year
Publication venue
arXiv preprint arXiv:2402.14460

External Links

Snippet

Active inference is a leading theory of perception, learning and decision making, which can be applied to neuroscience, robotics, psychology, and machine learning. Active inference is based on the expected free energy, which is mostly justified by the intuitive plausibility of its …
Continue reading at arxiv.org (PDF) (other versions)

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06N—COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computer systems based on biological models
    • G06N3/02—Computer systems based on biological models using neural network models
    • G06N3/04—Architectures, e.g. interconnection topology
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06N—COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computer systems based on biological models
    • G06N3/02—Computer systems based on biological models using neural network models
    • G06N3/06—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons
    • G06N3/063—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons using electronic means
    • G06N3/0635—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons using electronic means using analogue means
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06N—COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N99/00—Subject matter not provided for in other groups of this subclass
    • G06N99/005—Learning machines, i.e. computer in which a programme is changed according to experience gained by the machine itself during a complete run
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06N—COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computer systems based on biological models
    • G06N3/02—Computer systems based on biological models using neural network models
    • G06N3/08—Learning methods
    • G06N3/082—Learning methods modifying the architecture, e.g. adding or deleting nodes or connections, pruning
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06N—COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N5/00—Computer systems utilising knowledge based models
    • G06N5/04—Inference methods or devices
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06N—COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N7/00—Computer systems based on specific mathematical models
    • G06N7/005—Probabilistic networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06N—COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N5/00—Computer systems utilising knowledge based models
    • G06N5/02—Knowledge representation
    • G06N5/022—Knowledge engineering, knowledge acquisition

Similar Documents

Publication Publication Date Title
Van de Ven et al. Generative replay with feedback connections as a general strategy for continual learning
Champion et al. Reframing the expected free energy: Four formulations and a unification
CN108090558B (en) An automatic filling method for time series missing values based on long short-term memory network
Kjærulff Reduction of computational complexity in Bayesian networks through removal of weak dependences
Kutyniok The mathematics of artificial intelligence
US8478711B2 (en) System and method for data fusion with adaptive learning
Cooper A Bayesian method for causal modeling and discovery under selection
Tian et al. Computing posterior probabilities of structural features in Bayesian networks
Eslami et al. Just-in-time learning for fast and flexible inference
de Valpine Frequentist analysis of hierarchical models for population dynamics and demographic data
Singh et al. Inference with aggregate data: An optimal transport approach
Üney et al. Latent parameter estimation in fusion networks using separable likelihoods
DeMoss et al. Ditto: Offline imitation learning with world models
Champion et al. Deconstructing deep active inference
Bandyopadhyay et al. System of type-2 fuzzy differential equations and its applications
Kanjanatarakul et al. Distributed data fusion in the dempster-shafer framework
Da Costa et al. Natural selection finds natural gradient
Kaplan et al. Efficient subjective Bayesian network belief propagation for trees
US20240104370A1 (en) Modelling causation in machine learning
Dey et al. An Imbalanced Mean-Field Game Theoretical Large-Scale Multiagent Optimization With Constraints
Zagorecki Local probability distributions in Bayesian networks: Knowledge elicitation and inference
Cui et al. CLAP: Collaborative adaptation for patchwork learning
Tipaldi et al. Approximate covariance estimation in graphical approaches to SLAM
Bird et al. On the meaning of uncertainty for ethical AI: philosophy and practice
Ahmed et al. Stochastic Fusion Techniques for State Estimation.