Neural Network Workshop: Difference between revisions

From Noisebridge
Jump to navigation Jump to search
No edit summary
No edit summary
Line 11: Line 11:
=== List of Topics ===
=== List of Topics ===
*Math Preliminaries
*Math Preliminaries
**Universal Approximators: Kolmogorov's Theorem
**Universal Approximators: [http://en.wikipedia.org/wiki/Universal_approximation_theorem Cybenko's Theorem]
**Linear Algebra: vectors, matricies
**Linear Algebra: vectors, matricies
**Optimization Theory: error functions, gradients  
**Optimization Theory: error functions, gradients  

Revision as of 19:51, 23 December 2010

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

When: Tenatively January 26, 2011

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!

List of Topics

  • Math Preliminaries
    • Universal Approximators: Cybenko's Theorem
    • Linear Algebra: vectors, matricies
    • Optimization Theory: error functions, gradients
    • Machine Learning: regression, classification
  • Neural Networks
    • Basic Architecture
    • Activation Functions
    • Error Functions and Output Layers
      • Regression (univariate and multivariate)
      • Classification (binary and multi-class, logistic and softmax)
    • Training
      • Backpropagation
    • Implementation
      • Identifying Faces with Neural Nets
      • ??? Other such ideas

Software

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

Retrieved from "https://wiki.extremist.software/index.php?title=Neural_Network_Workshop&oldid=15285"