I’ve recently felt a bit stagnant at my job. I am an ML engineer, but frankly 90% of my work is essentially making sure that data tables run nicely and then running three Jupyter notebook cells to get models. There’s very little involved in here that actually requires modeling expertise. To be good at my job, the main skill I need is understanding everything around the model - the details involving the data, the details involving which probabilities to model, and the details involving when to actually call the model request.
To rectify this, I asked GPT-4o to make me a plan that teaches me neural network architectures. It’s split into two parts; essentially “intermediate” and “advanced”.
Learning Deep Learning All Deliverables List
LLM Rules - Learning Deep Learning