I need you to develop some software for me. I would like this software to be developed for Windows using Python. Enhancement of Lstm Algorithm
Right now I have implemented LSTM via Keras environment and average accuracy is about 85% and I would like to enhance the accuracy by modifying Lstm algorithm. Please note that I do not plan to play with Nw architecture, but making something clever to get better Lstm
What I have read is generally(most useful ones)are generally hybrid ones:
1)Lstm for feature selection and Svm for classification.
2)1d Cnn for feature selection and lstm for classification.
3)For a better approach,it might be tried to achieve feature selection via LSTM and classification via SVM or any algorith who can work well with LSTM.
You can reach me via 00905346967077