modeldbrepository / 190565 Goto Github PK
View Code? Open in Web Editor NEWSupervised learning in spiking neural networks with FORCE training (Nicola & Clopath 2017)
Home Page: https://modeldb.science/190565
Supervised learning in spiking neural networks with FORCE training (Nicola & Clopath 2017)
Home Page: https://modeldb.science/190565
Instructions for FORCE Training Code Wilten Nicola ([email protected]) The code is separated into folders named for their corresponding figure from the manuscript. The code is usually labelled NeuronModelFORCETask.m or NeuronModelTask.m for example THETALORENZ is the code used to run a network of theta neurons learning a trajectory generated from the Lorenz system. Some of the folders also contain matlab files for numerically integrating the supervisors (lorenz.m, vanderpol.m etc). Running the code NeuronModelFORCEtask.m trains a network to reproduce the dynamics of the supervisor using FORCE training. The code for Figure 4 (songbird example) and Figure 5 (movie replay example) does not contain the supervisor due to file size constraints. Users can however provide their own supervisors in these examples. Some folders contain pre-trained weight matrices saved in .mat files. These folders contain a file labelled NETWORKSIM.mat which loads the weight matrix, and simulates the pre-trained network with random initial conditions. Also note, that there is a slight discrepancy in the reported parameter set for the Izhikevich neuron model for one of the supplementary oscillatory examples, which has b = -2 ns/mv, vthresh = -19.2 mv instead if b = 0 ns/mv and vthresh = -20 mv, as reported. This does not affect convergence results for the supplementary oscillator figure but leads to slight differences in reported post-training firing rates for the supplementary oscillatory figure.
In "190565/CODE FOR FIGURE 5 (USER SUPPLIED SUPERVISOR)/IZFORCEMOVIE.m", the description reads,
"% Network of Izhikevich Neurons learns a song bird signal with a clock
% input. Note that you have to supply your own supervisor here due to file
% size limitations. The supervisor, zx should be a matrix of m x nt dimensional, where
% m is the dimension of the supervisor and nt is the number of time steps.
% RLS is applied until time T/2. The HDTS is stored as variable z2. Note
% that the code is written for an 8 second supervisor, nt should equal the
% length of z2."
The code is identical to that in "190565/CODE FOR FIGURE 4 (USER SUPPLIED SUPERVISOR)/IZSONGBIRDFORCE.m" except for the hardcoded length of the supervisor.
Neither script actually produces any of the images in figure 4 or figure 5 of the paper
Nicola, W., & Clopath, C. (2017).
Supervised learning in spiking neural networks with FORCE training.
Nature communications, 8(1), 1-15.
In particular, the "CODE FOR FIGURE 5" does not include any code for an internally generated HDTS.
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.