/PredyNet

Predictive coding -inspired generative models

Primary LanguageJupyter Notebook

PredyNet

Predictive coding-inspired generative models

The idea of this project is to experiment with implementations of predictive coding

Predictive coding is one of the several proposed architectures for learning and representing internal, or mental, models. The idea of mental models is an old one, but in its contemporary form it was pioneered by Kenneth Craik:

“One of the most fundamental properties of thought is its power of predicting events… If the organism carries a “small-scale model” of external reality and of its own possible actions in its head, it is able to try out various alternatives, conclude which is the best of them, react to future situations before they arise…”

Adapted from Keller & Hahnloser, 2009