Instructor:Andrew Ng,major in machine learning
TAs:Paul Baumstarck,major in machine learning and computer vision
Catie Chang,neuroscientist
Tom Do,major in computational biology
Zico Kolter,major in machine learning
Daniel Ramage,major in natural language processing
How many people are in th computer science department?A half.How many people are from EE?A fifth.How many biologers are there here?Just a few.Anyone from statistics?A few.So where the rest of you from?ICME.
Machine learning turns out that there are many programs or there are many applications that you can't program by hand.For example,if you want to get a computer to read handwritten characters,to read sort of handwritten digits,that actually turns out to be amazingly difficult to write a piece of software to take this input,an image of something that I wrote and to figure out just what it is to translate my cursive handwriting into ,to extract the characters I wrote out in longhand.
Learning algorithms.
Arthur Samuel(1959).Machine learning :Field of study that gives computers the ability to learn without being explicitly programmed.
Tom mitchell(1998)Well-posed learning problem:A computer program is said to learn from experience E with respect to some task T and some performance measure P,if its performance on T,as measured by P,imporves with experience E.
Supervised learning:where the varibles you're trying to predict is a discreat value.it's either 1 or 0.there are many learning problems where we'll have more than one input variable more than one input feature and use more than one varibles to try to predict.
Learning theory:
Unsupervised learning:
They can be used on many things like organizing computing clusters,social network analysis,market segmentation.
Cocktail party problem:independent component analysis
ICA algorithm
Reinforcement Learning algorithms flying helicopters:reward function.so reinforcement learning is I think of it as a way for you to specify what you want done,so you have to specify what is a 'good dog' and what is a 'bad dog' behavior.And then it's up to the learning algorithm to figure out how to maximize the 'good dog',reward signals and minimize the 'bad dog ' punishments.