Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Problem running the docs example #21

Open
DanielParraUnam opened this issue Oct 29, 2021 · 2 comments
Open

Problem running the docs example #21

DanielParraUnam opened this issue Oct 29, 2021 · 2 comments

Comments

@DanielParraUnam
Copy link

Hello,

I am a grad student very interested in implementing different STDP rules for DL image tasks. I just started and am having trouble running the docs example, in particular simulate! doesnt alter the state and the following line

LIFsim = simulate!(neuronLIF, (t)->0.4*exp(-4t), 0.001, 0.250, track_state=true)

simulates an static neuron for all the parameters I tried. I was wondering if someone could help me get started either debugging the docs example or with a working example of STDP

Thank you for your time!
Daniel,

P.D: tried it on Julia 1.4.2 and 1.6.2 in windows 10 (also there is a bug in the reset function, 0 should be a float64 0. )

@SBuercklin
Copy link
Collaborator

If you construct a Network with one Layer with one neuronLIF in it, does that work? It's possible that specifically the simulate!(::AbstractNeuron, ...) case is broken

@SBuercklin
Copy link
Collaborator

This works for me:

using WaspNet

lif = WaspNet.LIF()
l = Layer([lif], reshape([1.0], 1, 1))
net = Network([l])

LIFsim = simulate!(net, (t)->0.4*exp(-4t), 0.001, 0.250, track_state=true)

We could (probably should) add a method which generates this automatically if an AbstractNeuron is the object to be simulated

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants