Leabra7: a Python package for modeling recurrent, biologically-realistic neural networks

TL;DR

Leabra7 is a Python library that implements biologically-realistic recurrent neural networks using the LEABRA learning algorithm, enabling simulation and training of complex neural architectures with integration into Python's scientific ecosystem.

Contribution

It introduces Leabra7, a modern Python package that implements LEABRA-based recurrent neural networks, facilitating biologically-plausible modeling and machine learning applications.

Findings

Successfully modeled pattern-association tasks.

Classified the IRIS dataset using Leabra7 networks.

Demonstrated integration with Python's scientific stack.

Abstract

Emergent is a software package that uses the AdEx neural dynamics model and LEABRA learning algorithm to simulate and train arbitrary recurrent neural network architectures in a biologically-realistic manner. We present Leabra7, a complementary Python library that implements these same algorithms. Leabra7 is developed and distributed using modern software development principles, and integrates tightly with Python's scientific stack. We demonstrate recurrent Leabra7 networks using traditional pattern-association tasks and a standard machine learning task, classifying the IRIS dataset.