Start Date

8-5-2013 11:00 AM

Subjects

Neural networks (Computer science), Neural computers, Biologically-inspired computing

Description

We analyze the computational capability of Leaky Integrate-and-Fire (LIF) Neural Networks used as a reservoir (liquid) in the framework of Liquid State Machines (LSM). Maass et. al. investigated LIF neurons in LSM and their results showed that they are capable of noise-robust, parallel, and real-time computation. However, it still remains an open question how the network topology affects the computational capability of a reservoir. To address that question, we investigate the performance of the reservoir as a function of the average reservoir connectivity. We also show that the dynamics of the LIF reservoir is sensitive to changes in the average network connectivity, which is consistent with the results taken from RBN reservoirs. Our results are relevant for understanding of the computational capabilities of reservoirs made up of biologically-realistic neuron models for real-time processing of time- varying inputs.

Persistent Identifier

http://archives.pdx.edu/ds/psu/9482

Share

COinS
 
May 8th, 11:00 AM

Computational Capabilities of Leaky Integrate-and-Fire Neural Networks for Liquid State Machines

We analyze the computational capability of Leaky Integrate-and-Fire (LIF) Neural Networks used as a reservoir (liquid) in the framework of Liquid State Machines (LSM). Maass et. al. investigated LIF neurons in LSM and their results showed that they are capable of noise-robust, parallel, and real-time computation. However, it still remains an open question how the network topology affects the computational capability of a reservoir. To address that question, we investigate the performance of the reservoir as a function of the average reservoir connectivity. We also show that the dynamics of the LIF reservoir is sensitive to changes in the average network connectivity, which is consistent with the results taken from RBN reservoirs. Our results are relevant for understanding of the computational capabilities of reservoirs made up of biologically-realistic neuron models for real-time processing of time- varying inputs.