1 / 4

Limitations and Features of Neural Networks

Explore the limitations of backpropagation learning in neural networks and the features of Hebbian learning, including unsupervised learning, pattern recognition, and image compression. Discover the mathematical relationship to principle components analysis and clustering.

donaldboyd
Download Presentation

Limitations and Features of Neural Networks

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript

  1. Lecture 28B More on Neural Nets CSE 573 Artificial Intelligence I Henry Kautz Fall 2001 CSE 573

  2. Limitations of backpropagation learning • 1. Requires a supervisor to train the system. • 2. Does not allow feedback from the output layer to the input layer. (Networks with loops are called recurrent networks.) • 3. Requires very large number of trials to train the network effectively - no one-trial learning. • 4. Not biologically plausible: real neurons lack connections to do backpropagation. CSE 573

  3. Hebbian Learning When an axon of cell A is near enough to excite a cell B and repeatedly or persistently takes part in firing it, some growth process or metabolic change takes place in one or both cells such that A's efficiency, as one of the cells firing B, is increased (Hebb 1949) CSE 573

  4. Features of Hebbian Learning • Unsupervised • Most successful applications: • pattern recognition • image compression • Must add some way to prevent weights from growing without bounds – e.g., decay • Can use in networks with feedback loops • Mathematics closely related to principle components analysis – clustering CSE 573

More Related