[HTML][HTML] Where is the error? Hierarchical predictive coding through dendritic error computation
Top-down feedback in cortex is critical for guiding sensory processing, which has
prominently been formalized in the theory of hierarchical predictive coding (hPC). However …
prominently been formalized in the theory of hierarchical predictive coding (hPC). However …
[HTML][HTML] How particular is the physics of the free energy principle?
The free energy principle (FEP) states that any dynamical system can be interpreted as
performing Bayesian inference upon its surrounding environment. Although, in theory, the …
performing Bayesian inference upon its surrounding environment. Although, in theory, the …
The emperor's new Markov blankets
J Bruineberg, K Dołęga, J Dewhurst… - Behavioral and Brain …, 2022 - cambridge.org
The free energy principle, an influential framework in computational neuroscience and
theoretical neurobiology, starts from the assumption that living systems ensure adaptive …
theoretical neurobiology, starts from the assumption that living systems ensure adaptive …
The empirical status of predictive coding and active inference
Research on predictive processing models has focused largely on two specific algorithmic
theories: Predictive Coding for perception and Active Inference for decision-making. While …
theories: Predictive Coding for perception and Active Inference for decision-making. While …
Predictive coding approximates backprop along arbitrary computation graphs
Backpropagation of error (backprop) is a powerful algorithm for training machine learning
architectures through end-to-end differentiation. Recently it has been shown that backprop …
architectures through end-to-end differentiation. Recently it has been shown that backprop …
Predictive coding: Towards a future of deep learning beyond backpropagation?
The backpropagation of error algorithm used to train deep neural networks has been
fundamental to the successes of deep learning. However, it requires sequential backward …
fundamental to the successes of deep learning. However, it requires sequential backward …
Learning beyond sensations: how dreams organize neuronal representations
Semantic representations in higher sensory cortices form the basis for robust, yet flexible
behavior. These representations are acquired over the course of development in an …
behavior. These representations are acquired over the course of development in an …
Recurrent predictive coding models for associative memory employing covariance learning
The computational principles adopted by the hippocampus in associative memory (AM)
tasks have been one of the most studied topics in computational and theoretical …
tasks have been one of the most studied topics in computational and theoretical …
Learning on arbitrary graph topologies via predictive coding
Training with backpropagation (BP) in standard deep learning consists of two main steps: a
forward pass that maps a data point to its prediction, and a backward pass that propagates …
forward pass that maps a data point to its prediction, and a backward pass that propagates …
Kalman filters as the steady-state solution of gradient descent on variational free energy
M Baltieri, T Isomura - arXiv preprint arXiv:2111.10530, 2021 - arxiv.org
The Kalman filter is an algorithm for the estimation of hidden variables in dynamical systems
under linear Gauss-Markov assumptions with widespread applications across different …
under linear Gauss-Markov assumptions with widespread applications across different …