Programming Neural Networks with Python
by Rheinwerk Publishing, Inc, Dr. Joachim Steinwendner, Dr. Roland Schwaiger
4 Learning in a Simple Network
What does learning in a neural network mean? We’ll describe learning in this context and what that looks like in concrete terms. You’ll also see that you can learn in more than one way!
This chapter takes us back to the beginnings of learning for artificial neural networks (ANNs). In 1949, Donald Hebb discovered the effect that the connection between two neurons is strengthened if they fire simultaneously, which is the basic mechanism for learning and memory. Motivated by these discoveries, a directional learning strategy emerged called perceptron learning, which explained learning for datasets that are cleanly separable. Encouraged by the success of this learning approach and aware of its shortcomings, the next ...
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.
Read now
Unlock full access