Ted Talk (implications of computers that can learn):

 Arthur Samuel was the “father” of machine learning because in 1956 he wanted to get a computer to beat him at checkers. He had computer play against itself and learn through thousands of times. In the end it worked.

 There is such a thing as a machine learning practitioner. Google shows it is possible to find information using a computer algorithm. This algorithm uses machine learning. Amazon, netflix use machine learning to suggest products. Rather than being programed by hand, algorithms learned how to do this from data.

 Self driving cars are possible because of machine learning. The self driving car has driven a million miles without any accident. Deep learning is an algorithm inspired by how the human brain works. Theoretically, there are no limitations to what it can do. The more data and computation time it has, the better it gets.

 Computers can listen and understand. They can also see. There is a 6 percent error rate in image recognition in computers. More complex sentences are understandable because of deep learning. Nuanced sentences are understandable. Computers can recognize what sentences are about. Computers can also write. They can describe images without having seen them in that order before. Deep learning can cut a lot of time from tasks.