Comments (18)
The problem is when we try to use grad for optimizing weights, it has different point.
for grad to get another grad-> just through it
for grad to optimize -> it is quite different. need to get delta W for it. delta W is equal as deltaEXl(t)/deltaWgrad
from ra9.
from ra9.
LInear layer was well-worked, but after pooling layers, it did'nt works. So, I'll try to fix this error
from ra9.
there has a problem in linear layer too. need to review
from ra9.
ValueError: Incompatible shapes for broadcasting: (300, 784) and requested shape (64, 784)
might be the problem of transpose
from ra9.
loss.backward() didn't work due to dimension error
from ra9.
it is resolved
but need to test gradient
from ra9.
might be the problem of encoding or somehow?
from ra9.
It didn't work in fully-connected and xcnn_mnist, just swing away in range +- 1.x
from ra9.
Engine has problem. When you see engine in output, you need to elementwise multifiplying Time range(T in paper) but you matrix multiplicating grad so it went grad square indeed. need to change engine
from ra9.
#100 detailed-description
from ra9.
Not really. the real problem is the position of grad and gamma, matrix multiplication has directional factor so @jepetolee and @Dongyeongkim will fix it
from ra9.
#101 has been tested. and the solution is confirmed. this case is signed a die
from ra9.
the case which is opened: Convolution and pooling backward
from ra9.
need to test #102
from ra9.
mini-Batch algorithm need to be understood, it is likely to get an average of error gradient
from ra9.
Well the states of neurons which is based on batch data is different.
ex) 1,2,3 -> have different membrane potentials because data is different
grad is not equal, weight is equal, LIF' is not equal.
so the grad has different in regard to an element of batch.
from ra9.
need test but not now
from ra9.
Related Issues (20)
- Engine is the problem HOT 1
- Dropout Error HOT 1
- CANT FING BUGS!!!! HOT 1
- img2col error HOT 1
- Using grad to backward HOT 1
- TPU_Colab version HOT 1
- TPU_Cloud_support HOT 1
- The poisson Encoder might be wrecked by me LOL HOT 4
- Output NaN problem HOT 1
- Need to make Spike stochastic Gradient Descent Optimizer HOT 1
- Performance Enhancement HOT 6
- Loss function Bug HOT 1
- Dropout module HOT 1
- When v_current is set to zero, then it sustains the zero HOT 1
- The Pencoder code is different HOT 1
- Encoding Problem HOT 1
- Voltage rest value undefined. HOT 1
- memory leak HOT 1
- SpikeLoss grad function undefined HOT 1
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 ra9.