This shows you the differences between two versions of the page.
Both sides previous revision Previous revision Next revision | Previous revision Next revision Both sides next revision | ||
assignments:assignment6 [2016/11/02 19:37] asa |
assignments:assignment6 [2016/11/03 15:28] asa |
||
---|---|---|---|
Line 2: | Line 2: | ||
==== Assignment 6: Linear Regression with Theano ==== | ==== Assignment 6: Linear Regression with Theano ==== | ||
+ | |||
+ | This assignment is purely optional! | ||
**Due:** November 18th at 11:59pm | **Due:** November 18th at 11:59pm | ||
Line 28: | Line 30: | ||
We'll consider a simpler loss function: | We'll consider a simpler loss function: | ||
$$\log \cosh (h(\mathbf{x}) - y) ),$$ | $$\log \cosh (h(\mathbf{x}) - y) ),$$ | ||
- | called the Log-Cosh loss. Recall that $\cosh(z) = \frac{\exp{z} + \exp{-z}}{2}$. | + | called the Log-Cosh loss. Recall that $\cosh(z) = \frac{\exp{(z)} + \exp{(-z)}}{2}$. |
What you need to do for this assignment: | What you need to do for this assignment: | ||
Line 43: | Line 45: | ||
</code> | </code> | ||
- | In your code, follow the standard interface we have used in coding classifiers; the code I have shown for [[code:theano|logistic regression]] gives you most of what you need for the coding part of this assignment. | + | In your code, follow the standard interface we have used in coding classifiers; the code I have shown for [[code:theano|logistic regression]] gives you much of what you need for the coding part of this assignment. |
===== Submission ===== | ===== Submission ===== |