Opening Neural Networks
Neural Networks
- Length
- 53 min
- Level
- Undergraduate
- Recorded
- MIT2014
Chapter 1 of 7: Before the lecture
Derives backpropagation update equations and matches neural network topologies to geometric decision boundaries.
Mark Seifter examines neural networks through explicit multiplier and summation nodes. He derives formulas for sigmoid activations and performance functions. Seifter works through quiz problems that require executing one step of backpropagation with linear adders instead of sigmoids. The lecture connects neural network topology to classifier decision boundaries by matching specific network architectures to geometric regions. It concludes with an application of multi-layer architectures to logical functions like XOR.
Mark Seifter examines neural networks through explicit multiplier and summation nodes. He derives formulas for sigmoid activations and performance functions. Seifter works through quiz problems that require executing one step of backpropagation with linear adders instead of sigmoids. The lecture connects neural network topology to classifier decision boundaries by matching specific network architectures to geometric regions. It concludes with an application of multi-layer architectures to logical functions like XOR.

This lecture
Lecture 26 of 27 of Artificial Intelligence.
Choose a node to see how it connects to this lecture. What comes before is on the leftat the top. What comes after is on the rightat the bottom. The ring is what it teaches. People and places are above. Other lectures and books are below.
Press a chosen node again to open it.
Your comment is kept while you sign up.Sign in