CSSE 413: Day 7

Outline

• Basic properties of data sets:
  • Data set and NN are appropriately sized
  • Input of data set captures the domain to be modeled, avoids OOD cases
  • Desired output of data set has desired distribution.
• Splitting data sets for training and assessment
• Introduction to NN assignment - part 1
  • Tracing the learning algorithm of a perceptron
  • Tracing the learning algorithm of a very simple FFnet

Materials

• Training, Validation and Test Sets
• Inputs and desired outputs of a skewed data set.
• Inputs and desired outputs of a more realistic data set
• AND perceptron worksheet
• XOR FFnet worksheet