Question

find the partial derivative with respect to k of \[-\sum_{j=1}^{M}{\log(p(x_j|\sigma \cap \sum \cap k)) + const * k}\]

Answer 1

where const is a constant

Answer 2

This expression doesn't make sense. What, for instance does \( \sigma \cap \sum \cap k \) mean?

Answer 3

I don't know, I just saw that in the AI class.

Answer 4

it probably means given small sigma and big sigma and k

Answer 5

Oh, I see. Hm. Well, give me another day and I'll do my AI catch up. I bought the text book two days ago.

Answer 6

It's in unsupervised learning, Expectation Maximization Algorithm.