(Deep) Learn a Neural Net For Greater Good!
Neural networks and deep learning often appear scarier than they really are!
Both are fundamental to modern machine learning – many users of ML packages apply these techniques when using those tools, but do not always grok fully what happens beneath the surface. Other more engineering-oriented practitioners are put off entirely by the seeming complexity of deep learning.
During this talk, we will walk through a live-coding practicum (in a Jupyter Notebook slideshow). We will implement a feed-forward, fully-connected neural net in "numpy", initially training it via a for-loop to demonstrate core concepts, and then codify the neural network as an object-oriented style classifier with which one can fit and predict on one’s own data.
This talk caters to those with an intermediate math background (some exposure to calculus -- though perhaps many, many years ago), and some experience with Python. All who are interested in learning more about deep learning welcome!