Deep Learning Part II

Student with a laptop and a water bottle next to it listens attentively

This course follows on from (and requires completion of) part 1 (and the associated MOOC). It tackles more complex problems that require integrating a number of techniques. This includes both integrating multiple deep learning techniques, as well as combining classic machine learning techniques with deep learning. All methods will be introduced in the context of solving end-to-end real world modeling problems.

Curriculum Details

Prerequisites

familiarity with Python, git, and bash
familiarity with the content covered in Deep Learning Part 1, version 2, including the fastai library, a high-level wrapper for PyTorch.
attend in-person Monday evenings at our Downtown campus
commit 10 hours a week to course study

The deep learning, the fastai library, and PyTorch requirements can be fulfilled by:

completing the updated, in-person Deep Learning Part 1 course (first offered fall '17)
completing all 7 lessons of part 1 of the MOOC at course.fast.ai