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

(Request) Make code more easy to use #5

Open
thelemontree10 opened this issue Feb 12, 2016 · 1 comment
Open

(Request) Make code more easy to use #5

thelemontree10 opened this issue Feb 12, 2016 · 1 comment

Comments

@thelemontree10
Copy link

Hello zhongkaifu,

Your framework is very great but there are something I think you should change a little to get your code more easy to use. Can you change your code in the way that it can receive directly a matrix, a jagged array as input, have a train and predict method like here ? (The example)

http://accord-framework.net/docs/html/T_Accord_MachineLearning_VectorMachines_MulticlassSupportVectorMachine.htm

With this change, I think you will make a big milestone.

Regards

@zhongkaifu
Copy link
Owner

Thanks for your suggestion. I'm thinking about refactoring each neural network layer to abstract interface. If you have any idea about it, please let me know. Thanks.

zhongkaifu added a commit that referenced this issue Feb 5, 2017
…hidden layer is more than 1

#2. Improve training part of bi-directional RNN. We don't re-run forward before updating weights
#3. Fix bugs in Dropout layer
#4. Change hidden layer settings in configuration file.
#5. Refactoring code
zhongkaifu added a commit that referenced this issue May 3, 2017
#2. Improve training performnce ~ 300% up
#3. Fix learning rate update bug
#4. Apply SIMD instruction to update error in layers
#5. Code refactoring
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