Ecosyste.ms: Packages

proxy.golang.org : github.com/emer/leabra

Package leabra is the overall repository for all standard Leabra algorithm code implemented in the Go language (golang) with Python wrappers. This top-level of the repository has no functional code -- everything is organized into the following sub-repositories: * leabra: the core standard implementation with the minimal set of standard mechanisms exclusively using rate-coded neurons -- there are too many differences with spiking, so that is now separated out into a different package. * deep: the DeepLeabra version which performs predictive learning by attempting to predict the activation states over the Pulvinar nucleus of the thalamus (in posterior sensory cortex), which are driven phasically every 100 msec by deep layer 5 intrinsic bursting (5IB) neurons that have strong focal (essentially 1-to-1) connections onto the Pulvinar Thalamic Relay Cell (TRC) neurons. * examples: these actually compile into runnable programs and provide the starting point for your own simulations. examples/ra25 is the place to start for the most basic standard template of a model that learns a small set of input / output patterns in a classic supervised-learning manner. * python: follow the instructions in the README.md file to build a python wrapper that will allow you to fully control the models using Python.

Registry - Source - Documentation - JSON
purl: pkg:golang/github.com/emer/leabra
Keywords: artificial-intelligence, artificial-neural-networks, cognitive-neuroscience, cognitive-science, computational-neuroscience, emergent, go, golang, neural-network
License: BSD-3-Clause
Latest release: 3 months ago
First release: almost 5 years ago
Namespace: github.com/emer
Dependent packages: 14
Dependent repositories: 14
Stars: 55 on GitHub
Forks: 20 on GitHub
See more repository details: repos.ecosyste.ms
Last synced: 29 days ago

• Readme
• Versions 70
• Dependent Packages 14
• Maintainers 0
• Related Packages 1