Search Results for author:
Found 7 papers, 3 papers with code
On Predictive planning and counterfactual learning in active inference
Given the rapid advancement of artificial intelligence, understanding the foundations of intelligent behaviour is increasingly important.
Active Inference and Intentional Behaviour
First, we simulate the aforementioned in vitro experiments, in which neuronal cultures spontaneously learn to play Pong, by implementing nested, free energy minimising processes.
Bayesian mechanics of self-organising systems
This work shows that the Hamiltonian of generic dynamical systems constitutes a class of generative models, thus rendering their Helmholtz energy naturally equivalent to variational free energy under the identified generative model.
Kalman filters as the steady-state solution of gradient descent on variational free energy
In this work, we present a straightforward derivation of Kalman filters consistent with active inference via a variational treatment of free energy minimisation in terms of gradient descent.
Quadratic speedup of global search using a biased crossover of two good solutions
Mathematical analyses demonstrate that a combination of the gradient descent algorithm and the selection and crossover algorithm--with a biased crossover weight--maximises the search efficiency.
Dimensionality reduction to maximize prediction generalization capability
Generalization of time series prediction remains an important open issue in machine learning, wherein earlier methods have either large generalization error or local minima.
On the achievability of blind source separation for high-dimensional nonlinear source mixtures
This work theoretically validates that a cascade of linear PCA and ICA can solve a nonlinear BSS problem accurately -- when the sensory inputs are generated from hidden sources via nonlinear mappings with sufficient dimensionality.
