davrot/nnmf_24a
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Update README.md

Browse source
This commit is contained in:
David Rotermund 2024-07-10 16:09:16 +02:00 committed by GitHub
parent 71165d2a14
commit 388b83c264
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 17 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

17
README.md
View file

@ -1 +1,18 @@
Refinement of the approach for deep NNMF networks shown in:
```
Competitive performance and superior noise robustness of a non-negative deep convolutional spiking network
David Rotermund, Alberto Garcia-Ortiz, Kaus R. Pawelzik
https://www.biorxiv.org/content/10.1101/2023.04.22.537923v1
```
Now a normal ADAM optimiser will work.
The BP learning rule is taken from here (it was derived for a spike-based SbS system, but it works exactly the same for NNMF):
```
Back-Propagation Learning in Deep Spike-By-Spike Networks
David Rotermund and Klaus R. Pawelzik
https://www.frontiersin.org/journals/computational-neuroscience/articles/10.3389/fncom.2019.00055/full
```