Machine Learning Summer School
13-17 June 2011, Singapore
The home page for the MLSS world series is http://www.mlss.cc/
Lecture notes for previous events: http://www.springerlink.com/content/lrh41y849xdh/
Sunday, February 20, 2011
Thursday, February 17, 2011
[NN] A guide to recurrent neural network and backpropagation
This doc is a rather simple introduction to Recurrent Neural Network giving a basic understanding of RNN. 
Modeling time series, we can use either feedforward networks or RNN:
1) Adopting temporal windows on the input feature for feed forward NN, i.e. the tapped delay line memory in this paper
2) RNN is inherently capable of modeling the temporal information in the input sequence due to its recurrent characteristic
One major concern is the simple RNN only make use of the previous input information, which may not be sufficient especially for speech signals.
To incorporate more temporal information a complex system is required and the structure after unfolding is illustrated below:
Will this more complex system beat the feed forward NN with similar model complexity?
Another issue is the RNN only utilizes the historical information in the time series, while for windowing in feed forward NN, we can actually employ both the history and future information for current frame prediction.
However, feed forward NN process the current input and the context information with the same set of model parameter, which may not be the best way.
Maybe the first thing to try is just to experiment with RNN see whether it gives any promising results.
Wednesday, February 16, 2011
Introduction To Bayesian Inference
Download slides: 
In the progress of learning his wonderful book Pattern Recognition and Machine Learning
Probabilistic Models for Computational Linguistics
Time to learn more basic and fundamental stuffs for my research
Thursday, January 27, 2011
[Conference] PASCAL CHiME
PASCAL CHiME Speech Separation and Recognition Challenge Deadline: April 14, 2011
Workshop: September 1, 2011, Florence, Italy http://www.dcs.shef.ac.uk/spandh/chime/challenge.html
Workshop: September 1, 2011, Florence, Italy http://www.dcs.shef.ac.uk/spandh/chime/challenge.html
Wednesday, January 26, 2011
[Speech] FFT algorithm
The FFT algorithm implemented in the HTK is the Decimation-In-Time FFT algorithm as detailed explained in the attached file. The computation could be reflected in the following flow graph ( 8-poing DFT ): 
A minor difference is that in the HTK implementation, the Wn=exp(j * 2 * pi / n), while in common the Wn adopted is Wn=exp(-j * 2 * pi).
The above FFT algorithm only deals with complex numbers. To do DFT on the real valued signal sequence we need a real version of the FFT, for which we could utilize the complex FFT. In the second document from Texas Instrument, they give a fast implementation of the FFT for real valued sequences ( on page 12-19). The algorithm is illustrated briefly in following figure:
Friday, January 21, 2011
Subscribe to:
Posts (Atom)