Comments (3)
The Multi-Gaussian is taken from the paper and is a weighted sum of multiple Gaussians. What you are referring to is the periodic version of surrogate gradient functions such as PeriodicExponential. It's true that we might need a PeriodicMultiGaussian to see how it performs.
from sinabs.
Aha that makes sense! Thanks for the clarification. Alright, I will raise another issues/feature request for a Periodic version of the Gaussian.
from sinabs.
Turns out the MultiGaussian was just a single Gaussian. This is fixed in 0070a90
from sinabs.
Related Issues (20)
- Merge sinabs-dynapcnn to sinabs HOT 3
- Add documentation for NIR support
- Transition from SNNAnalyzer to hooks HOT 5
- DynapcnnNetwork conversion cannot handle Identity module
- Failing dynapcnn tests HOT 5
- address failing tests HOT 2
- Split tutorial on LeNet into two languages
- Question: Where does the weight transfer happen? HOT 3
- Github actions node16 deprecation warnings
- Add black linting to CI/CD HOT 1
- Codecov action in the pipeline silently fails to upload coverage HOT 2
- hooks.py missing variables in namespace.
- New release v2.0 HOT 9
- More sensible change log HOT 3
- Installation instructions to mention risks of development install.
- Missing link in speck/overview.md to leak_neuron tutorial
- Set up the CI with the chips plugged in for tests with hardware
- Add unit tests for errors and warnings that should be raised. (Check coverage report)
- Conversion error mitigation HOT 1
- Update tutorial on reading outputs from hardware
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from sinabs.