Difference between revisions of "DMelt:AI/4 Recurrent NN and LSTM"

From jWork.ORG
Jump to: navigation, search
m
m
 
Line 2: Line 2:
  
  
Recurrent Neural Networks (RNN) and Long Short-Term Memory Networks (LSTM) are included using <javadoc sc>recunn/</javadoc> library.
+
Recurrent Neural Networks (RNN) and Long Short-Term Memory Networks (LSTM) are included using <javadoc sc>recunn/</javadoc> Java library under the MIT license.
 
Recurrent networks and their popular type, LSTM,  
 
Recurrent networks and their popular type, LSTM,  
 
are artificial neural network designed to recognize patterns in sequences of data, such as text, sequences, handwriting, the spoken words, or numerical times series.
 
are artificial neural network designed to recognize patterns in sequences of data, such as text, sequences, handwriting, the spoken words, or numerical times series.
  
 
Here is a demo that reads sentences from Paul Graham's essays,  encoding Paul Graham's knowledge into the weights of the Recurrent Networks.  
 
Here is a demo that reads sentences from Paul Graham's essays,  encoding Paul Graham's knowledge into the weights of the Recurrent Networks.  
 +
The long-term goal of the project then is to generate startup wisdom at will. Feel free to train on whatever data you wish, and to experiment with the parameters. If you want more impressive models you have to increase the sizes of hidden layers, and maybe slightly the letter vectors.
  
 
<jcode lang="python">
 
<jcode lang="python">

Latest revision as of 19:27, 6 December 2017

Recurrent Neural Networks (RNN) and LSTM

Recurrent Neural Networks (RNN) and Long Short-Term Memory Networks (LSTM) are included using recunn/ Java library under the MIT license. Recurrent networks and their popular type, LSTM, are artificial neural network designed to recognize patterns in sequences of data, such as text, sequences, handwriting, the spoken words, or numerical times series.

Here is a demo that reads sentences from Paul Graham's essays, encoding Paul Graham's knowledge into the weights of the Recurrent Networks. The long-term goal of the project then is to generate startup wisdom at will. Feel free to train on whatever data you wish, and to experiment with the parameters. If you want more impressive models you have to increase the sizes of hidden layers, and maybe slightly the letter vectors.

The above example is based on JavaScript library http://cs.stanford.edu/people/karpathy/recurrentjs/