search

akusok / hpelm

High performance implementation of Extreme Learning Machines (fast randomized neural networks).
Other
191 stars 61 forks source link

Dimensionality of input/output data parameters annoying #3

Closed mertyildiran closed 8 years ago

mertyildiran commented 8 years ago

Could we remove dimensionality of input/output data constraints because it's really bothering me when I'm trying to train same network with arbitrary length of data.

I'm talking about the simple functionality like in this project: https://github.com/lepisma/ELM.jl

I'm suffering this problem in here: https://github.com/mertyildiran/Cerebrum/blob/f81351a8c27a4cf6fc76bf79fa35e2c8ed49ef75/cerebrum/neuralnet/weaver.py

I don't want to limit the length of input. In ELM.jl project output is also arbitrary and depends on the length of the input. I can crop the output or fill with zeros but I don't want to limit the input length.

Do you have any idea? Thanks a lot for this great library.

mertyildiran commented 8 years ago

I think I was wrong about ELM.jl library. But anyway, how can I get around from this dimensionality problem?

mertyildiran commented 8 years ago

It was a stupid question, I'm so sorry. I'm closing this issue.

akusok commented 8 years ago

Hello Mehmet,

The input dimensionality is used for automatic generation of neurons before ELM sees any data. If you still want it removed - I can do that, but then generation of neurons has to be delayed until an ELM gets training data, and that complicates the code somewhat.

Anyway, hope that you like the toolbox. Good luck with your project!

Best regards, Anton Akusok

Sent from my iPad

On 18 Apr 2016, at 10:04, Mehmet Mert Yıldıran notifications@github.com wrote:

Could we remove dimensionality of input/output data constraints because it's really bothering me when I'm trying to train same network with arbitrary length of data.

I'm talking about the simple functionality like in this project: https://github.com/lepisma/ELM.jl

I'm suffering this problem in here: https://github.com/mertyildiran/Cerebrum/blob/f81351a8c27a4cf6fc76bf79fa35e2c8ed49ef75/cerebrum/neuralnet/weaver.py

I don't want to limit the length of input. In ELM.jl project output is also arbitrary and depends on the length of the input. I can crop the output or fill with zeros but I don't want to limit the input length.

Do you have any idea? Thanks a lot for this great library.

— You are receiving this because you are subscribed to this thread. Reply to this email directly or view it on GitHub