Just a few links to various resources which may be useful for learning machine learning (pun intended).

Machine Learning course by Andrew Ng on Coursera: https://www.coursera.org/course/ml

“The Elements of Statistical Learning: Data Mining, Inference, and Prediction” book http://statweb.stanford.edu/~tibs/ElemStatLearn/printings/ESLII_print10.pdf

Various guides for getting started:

http://thunderboltlabs.com/blog/2013/11/09/getting-started-with-machine-learning/

http://abeautifulwww.com/2009/10/11/guide-to-getting-started-in-machine-learning/

Datasets:

MNIST: hand-written digits http://yann.lecun.com/exdb/mnist/

LabelMe: digital images with annotations http://en.wikipedia.org/wiki/LabelMe

UCI Machine Learning Repository contains 299 data sets for regression, classification, clustering, recommendation systems; from poker and movies to volcanoes on Venus and yacht hydrodynamics. https://archive.ics.uci.edu/ml/datasets.html

Datasets for computer vision problems: http://www.cvpapers.com/datasets.html

Kaggle competitions can be a good source of datasets and of real world machine learning problems. http://www.kaggle.com/