vix.ing · top · new · best · stats · spec

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

2018/09/11 by C. Daniel Greenidge, Greenidge, C. Daniel, Noam Miller +3
Computer Science · Neuroscience · #FOS: Biological sciences #FOS: Computer and information sciences #Neural Networks and Applications #Neural Networks and Reservoir Computing #Neural and Evolutionary Computing (cs.NE) #Neural dynamics and brain function #Neurons and Cognition (q-bio.NC)

paper · pdf · doi:10.48550/arxiv.1809.04166

openalex publication_date 2018/09/11 · openalex created_date 2022/08/03 · openalex updated_date 2026/07/28

Abstract

Emergent is a software package that uses the AdEx neural dynamics model and\nLEABRA learning algorithm to simulate and train arbitrary recurrent neural\nnetwork architectures in a biologically-realistic manner. We present Leabra7, a\ncomplementary Python library that implements these same algorithms. Leabra7 is\ndeveloped and distributed using modern software development principles, and\nintegrates tightly with Python's scientific stack. We demonstrate recurrent\nLeabra7 networks using traditional pattern-association tasks and a standard\nmachine learning task, classifying the IRIS dataset.\n

Citations

Related