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

Abstract

Emergent (Aisa, Mingus, & O'Reilly, 2008) is a software package that uses the AdEx neural dynamics model (Brette & Gerstner, 2005) and LEABRA learning algorithm (O'Reilly, 1996) to simulate and train arbitrary recurrent neural network architectures in a biologically-realistic manner. We present Leabra7 (Greenidge & Miller, 2018), 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.