Suppose you want to optimize the mean squared loss (page 270) for the sigmoid of a linear
Question:
Suppose you want to optimize the mean squared loss (page 270)
for the sigmoid of a linear function.
(a) Modify the algorithm of Figure 7.12 (page 292) so that the update is proportional to the gradient of the squared error. Note that this question assumes you know differential calculus, in particular, the chain rule for differentiation.
(b) Does this work better than the algorithm that minimizes log loss when evaluated according to the squared error?
Fantastic news! We've Found the answer you've been seeking!
Step by Step Answer:
Related Book For
Artificial Intelligence: Foundations Of Computational Agents
ISBN: 9781009258197
3rd Edition
Authors: David L. Poole , Alan K. Mackworth
Question Posted: