Neural Networks

Understand some of the theory behind neural networks 2. [...] Work on large-scale problems 7 Course Objectives: By the end of the course you will be able to…1. [...] Understanding some of the theory behind neural networks 2. [...] Build your own neural net components and tools – Part 1s of your homeworks – Bonus problems 3. [...] Understanding some of the theory behind neural networks 2. [...] Work on large-scale problems – Part 2s of your homeworks 9 Course Objectives: By the end of the course you will be able to…1. [...] Understanding some of the theory behind neural networks 2. [...] Work on large-scale problems • Course projects may relate to 1, 2 or 3 10 Course Objectives: By the end of the course you will be able to…Lecture Style • My lecture style is verbose, with lots of visualization • Many many slides – With a lot of animation • Given a choice between deriving an equation symbolically, and explaining it with 30 slides of pictures and animation, I usually choose the l [...] London: Smith, Elder and Co • Neurons connect to other neurons. The processing/capacity of the brain is a function of these connections • Connectionist machines emulate this structure 46Connectionist Machines • Network of processing elements • All world knowledge is stored in the connections between the elements 47Connectionist Machines • Neural networks are connectionist machines – As oppose [...] 109NNets in AI • The network is a function – Given an input, it computes the function layer wise to predict an output • More generally, given one or more inputs, predicts one or more outputs 110These tasks are functions • Each of these boxes is actually a function – E.g f: Image Caption N.