Neural Network Workshop

What: A hands-on workshop courtesy of the Machine Learning Group using Neural Networks that includes both the theory and practical implementation.

When: January 26, 2011 7:00pm - 10:00pm

Why: To raise Neural Network Awareness (NNA) and money for Noisebridge. Donations towards Noisebridge will be encouraged and appreciated.

Where: In the back classroom

Who: Anyone who wants to participate, either come and learn or help teach. Join the mailing list!. The math will be explained, but is not essential to totally understand in order to work with the examples given.

Workshop Overview, Resources

• Math Preliminaries
  • Universal Function Approximators
    • Cybenko's Theorem
    • Some guy's master thesis
  • Linear Algebra: vectors, matricies
  • Optimization Theory: error functions, gradients
  • Machine Learning: regression, classification
• Neural Networks
  • Basic Architecture
  • Activation Functions
    • Which activation functions are good? Hornik's 1991 Paper
  • Error Functions and Output Layers
    • Regression (univariate and multivariate)
    • Classification (binary and multi-class, logistic and softmax)
  • Training
    • Backpropagation
  • Implementation
    • Face or not a Face? Binary Classification with Neural Nets

Volunteers

Put your name down here to volunteer and contact Mike S for coordination:

• Mike S

Software

This is just a list of packages used for constructing and training neural networks:

• FANN
• Encog
• neuroph
• Torch5
• PyNN (Biophysical Neural Nets)