3 comments

[ 3.0 ms ] story [ 15.9 ms ] thread
Great introduction to ML algorithms. I would also like to recommend the Coursera course taught by Andrew Ng for a practical starting up in this powerful field.
The problem is that this guy has no clue.

- A naive Bayes classifier is not a Bayesian method. It's just using Bayes rule, while Bayesian methods marginalize out the parameters.

- Regression and classification are different things. And, ironically, logistic regression is a classifier.

- Neither Linear Discriminant Analysis nor radial basis functions are kernel methods.

- EM is not a clustering method, it is an optimization algorithm for probabilistic models of a specific structure.

- Learning vector quantization is not a neural net.

- ...