Neuromorphic Engineering Book

Welcome
Preliminaries
I. Introduction
II. Scientist perspective
III. Architect perspective
IV. Algorithm designer perspective

Powered by GitBook

On this page

Python / Nengo demonstration
Rectified linear and NEF's LIF neurons
LIF neuron response to a sinusoidal input
Two LIF neurons with the same intercept (0.5) and op-posing encoders
50 LIF neurons with uniformly distributed maximal spiking rates and randomized intercepts.
Two LIF-based stimulus decoding
50 LIF-based stimulus decoding
Exponentially decaying filters
Two convolved LIF-based stimulus decodings
50 convolved LIF-based stimulus decoding.
Representation of f(x) = x (randomly distributed tuning)
Representation of f(x) = x (uniformly distributed tuning)
Representation of f(x) = x (intercepts = -0.2)
Five most important basis functions and variation drop for 1,000 randomly tuned neurons.
Five most important basis functions and variation drop for 1,000 uniformly tuned neurons.
High dimensional representation
Four basis functions for a 500 2D neurons ensemble
Activity analysis of ensembles with various dimensions
Activity analysis for redistributed neurons within an ensemble of 32 dimensions.def find_x_for_p(p, d):

Was this helpful?

IV. Algorithm designer perspective

12. The neural engineering framework

NEF: Representation

Chapter 12.1.1

Previous12. The neural engineering framework NextNEF: Transformation

Last updated 11 months ago

Was this helpful?