Deep learning is essentially “neural networks on steroids” and it lies at the core of the most intriguing and powerful applications of artificial intelligence.
But how does the computer, faced with a huge array of pixel values, know what’s an eye, a nose, etc.? Deep learning provides the power to learn these features – starting out by learning more primitive constructs (e.g. the edge between one color and another.)
Let Alan Blair, award-winning professor and AI researcher at the University of New South Wales (Australia), be your guide, answering your questions and comments, in:
You will use Tensorflow, first to create a linear classifier and neural net, then to configure a convolutional neural network for use with an image recognition case study. Additional concepts covered include recurrent networks, representation learning, “long short term memory,” (LSTM) and deep generative models.
The course takes place online at Statistics.com in a series of weekly lesson and assignments, and requires about 15 hours/week. Participate at your own convenience; there are no set times when you are required to be online.
We hope to see you in this exploration of this key statistical component of AI!