Difference between revisions of "VS298 (Fall 06): Suggested projects"

From RedwoodCenter
Jump to navigationJump to search
Line 3: Line 3:
 
* '''Recognition of handwritten digits.'''  Train a MLP to classify handwritten digits 0-9.  You can get some training data [http://yann.lecun.com/exdb/mnist/ here].  You may wish to follow the convolutional network methodology of [http://yann.lecun.com/exdb/lenet/index.html Yann LeCun] (try the simpler, [http://yann.lecun.com/exdb/publis/pdf/lecun-89e.pdf earlier model]), or invent your own method.   
 
* '''Recognition of handwritten digits.'''  Train a MLP to classify handwritten digits 0-9.  You can get some training data [http://yann.lecun.com/exdb/mnist/ here].  You may wish to follow the convolutional network methodology of [http://yann.lecun.com/exdb/lenet/index.html Yann LeCun] (try the simpler, [http://yann.lecun.com/exdb/publis/pdf/lecun-89e.pdf earlier model]), or invent your own method.   
  
* Foldiak network
+
* '''Sparse coding and decorrelation.'''  Implement [http://redwood.berkeley.edu/~amir/vs298/foldiak90.pdf Peter Foldiak's network] and train it on the handwritten digits above to learn the features of this data.  You may wish to then try supervised learning on the learned features to see if it has simplified the classification problem.
  
* Cortical maps
+
* '''Cortical maps.''' 
  
 
* Feedforward vs. Recurrent weights in networks
 
* Feedforward vs. Recurrent weights in networks

Revision as of 01:59, 23 October 2006

  • NETtalk. Train a multi-layer perceptron to convert text to speech. You can get Sejnowski & Rosenberg's original paper and the data they used here. (You will need a DECtalk speech synthesizer to play the phonemes - you can probably pick up a used one online.)
  • Recognition of handwritten digits. Train a MLP to classify handwritten digits 0-9. You can get some training data here. You may wish to follow the convolutional network methodology of Yann LeCun (try the simpler, earlier model), or invent your own method.
  • Sparse coding and decorrelation. Implement Peter Foldiak's network and train it on the handwritten digits above to learn the features of this data. You may wish to then try supervised learning on the learned features to see if it has simplified the classification problem.
  • Cortical maps.
  • Feedforward vs. Recurrent weights in networks
  • Restricted Boltzmann machines
  • Integrate-and-fire model neuron