A few weeks ago I got laid off, along with a significant number of other folks where I worked. I've been looking for a new opportunity and have also decided to get back into machine learning. Here are a few resources that I found useful on the way.
Websites
Books
- The Hundred-Page Machine Mearning Book by Andriy Burkov
- The Hundred-Page Language Models Book, also by Andriy Burkov
- Designing Mahcine Learning Systems by Chip Huyen
- Rules of Machine Learning: Best Practices for ML Engineering by Martin Zinkevich
- Machine Learning Interviews Book by Chip Huyen
- Machine Learning Technical Interviews
Codestral suggestions as I typed this post
- Coursera Machine Learning Course - Andrew Ng's course on Coursera is great and it has a lot of practical exercises. It's also free.
- Stanford CS231n: Convolutional Neural Networks for Visual Recognition - This course is taught by Fei-Fei Li and Andrej Karpathy. It's a great introduction to convolutional neural networks.
Design System for Machine Learning
what interviewers look for
- Most candidates know the model classes (linear, decision trees, LSTM, convolutional neural networks) and memorize the relevant information
- the interesting bits in machine learning systems interviews are
- data cleaning
- data preparation
- logging
- evaluation metrics
- scalable inference
- feature stores (recommenders/rankers)
- the ability to divide and conquer the problem:
- Can the candidate break down the open ended problem into simple components (building blocks)
- Can the candidate identify which blocks require machine learning and which do not
- Can a person define the problem, identify relevant metrics, ideate on data sources and possible important features, understands deeply what machine learning can do.