Comments (4)
@happynear
This is a good question, and should be a common one. Of course one can tune the gamma based on the validation set, but this is really annoying. We have tried that, but soon we came up with another idea to implement our formulation and avoid overfitting.
So if you look at our experiment configuration files, you can see we adopted an early stopping policy during the training process, i.e, we first train the network with DSN for a number of epochs (which is determined by validation) and we discard all the companion losses and continue to train the network with only the output loss.
The gamma now is implicitly and dynamically determined by the loss value achieved at the time when we early stop, empirically this is essential for DSN to achieve good performance.
from dsn.
In @happynear comment, \gamma is setted to prevent the hinge loss to be 0.
However, from my point of view, \gamma is setted to
But I don't know the purpose to vanish the gradient in the paper. Is it for speed up the training process because it can skip part of BP algorithm? @s9xie
from dsn.
@happynear @zhangliliang Sorry yes it is not "preventing hinge to be zero" but vanishing it. I assume it is a typo in original question?
In our paper we have explained that:
"This way, the overall goal of producing good classification of the output layer is not altered and the companion objective just acts as a proxy or regularization."
Intuitively we should emphasize the role of the overall loss during the training, this "early stop" policy can be a good way to avoid over-fitting the lower layers into the local loss.
from dsn.
@s9xie I am working on implementing your method. So, you mean that you don't explicitly use gamma
, right? Actually, I am also curious about the other hyperparameter alpha
, which requires exponential search space when layer increases. When I see your paper, you use relatively small architecture, i.e. 3-layer NN. How to tune this hyperparameter?
Thanks,
from dsn.
Related Issues (11)
- On weights of the loss layers HOT 2
- Getting error while reproducing results from shared processed Leveldb files
- About the "relu_cccp6"
- release configuration of MNIST etc. HOT 1
- Where to find the cifar-100 train/test/solver configure file HOT 4
- How to make DSN runnable with recent Caffe?
- Theano code for DSN? HOT 1
- Is SVM implemented?
- SVHN dataset, is there config file to train and test? HOT 1
- Number of parameters seems larger than NIN paper unlike your paper statement?
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 dsn.