The Andrew Ng's Coursera courses are so good I'm just going to finish out all 5 courses in the Deep learning Specialization. This will give me the foundational knowledge I'm looking for while I do some small side projects to test some implementations and learning the tools. For my first project I'm going to implement the functionality of an AI Scribe. AI scribes are very popular in primary care right now so some knowledge of how they're implemented will be informative for me both educationally and for evaluating the privacy & security of these products at work.

Week 4 Material

Improving Deep Neural Networks: Hyperparameter Tuning, Regularization and Optimization - Week 2

This week covered the following topics:

• Apply optimization methods such as (Stochastic) Gradient Descent, Momentum, RMSProp and Adam
• Use random minibatches to accelerate convergence and improve optimization
• Describe the benefits of learning rate decay and apply it to your optimization

The more I progress on learning the basics of deep learning the more excited I'm getting about getting to reading the research and running my own experiments. There's so much here that's ripe for progress and new ideas. It shouldn't be hard to find a question that's interesting to me and contributes to the research.

My ChatGPT generated syllabus recommended doing the fast.ai CNN lesson which I did not get to due to working on the Coursera course. I may try to get back to this through the week but I'm really eager to just plough through all 5 Coursera courses at this point so that I have enough foundational knowledge to start reading papers. Not enough hours in the day.