So, I've been trying to learn Machine Learning. It's been an open subject for me for years; I remember going to university to learn computer science (which took me a long time to begin with -- a story for another day perhaps) already with the fuzzy idea of going into Machine Learning.
Prior to that I had studied Literature/Linguistics, and already I had the fuzzy idea there of specializing in Neurolinguistics. In the end I only did some introductory subjects on the matter before dropping out. Dropping out is sort of what I do, by the way. I'm trying to change this aspect of my personality, and actually starting this blog has to do with that.
Anyway, I've always been interested in ML, but for several years now I've been content with reading Wikipedia on it from time to time. And to sit back and sort of spectate about how the field has been advancing. Only a month ago I decided to get into it more seriously, and I've been doing the well-rated (and by now sort of classic) Coursera course on the matter (Andrew Ng's). It's been great fun, and I intend to do it to completion (not to drop out this time). What comes after that, I'm not completely sure right now, but that's sort of exciting on its own right.
- natural language processing
**Machine Learning, a subset of AI, uses computer algorithms to analyze data and make intelligent decisions based on what it has learned. **
Uses models not rules.
A solid reference I've used heavily is Models for machine learning from the IBM developer blog.
Machine Learning Models
The three types of machine learning
Go back to the AI Glossary
A program or system that builds (trains) a predictive model from input data. The system uses the learned model to make useful predictions from new (never-before-seen) data drawn from the same distribution as the one used to train the model. Machine learning also refers to the field of study concerned with these programs or systems.