Welcome back to SIGAI! We'll be covering some administrative needs – like how we're doing lectures/workshops and what we expect of coordinators, since we'll have elections in March. Then we'll go over some math to check everyone's background so you're uber prepared for next week! Once we've covered that, we'll go over Gradient Descent and get a rough idea of how it works – this is integral to almost all our content this semester.
Here, we'll dive, head first, into the nitty-gritty of Neural Networks, how they work, what Gradient Descent achieves for them, and how Neural Networks act on the feedback that Gradient Descent derives.
We'll take what we learned last week and actually write up a Neural Network to train on the MNIST dataset, to recognize hand-written digits with about 92% accuracy.