Ask HN: Full-on machine learning for 2020, what are the best resources?

Re:Ask HN: Full-on machine learning for 2020, what are the b... by autokad on Tuesday December 31, 2019 @03:50PM (#21924622)

Does anyone have any resources for people with more advanced ML experience?

[ Parent | on HN ]

Re:Ask HN: Full-on machine learning for 2020, what are the b... by wish5031 on Tuesday December 31, 2019 @04:11PM (#21924772)

Have you read Goodfellow / Bengio / Courville’s deep learning book? The later chapters go in more depth than most other resources I’ve found.

[ Parent | on HN ]

Re:Ask HN: Full-on machine learning for 2020, what are the b... by boltzmannbrain on Tuesday December 31, 2019 @04:02PM (#21924718)

1. Find a paper you like/admire

2. Implement their methods from scratch (i.e. numpy not pytorch)

3. Experiment a bit, tweaking the models/algs to gain intuition

4. Repeat 1-3

[ Parent | on HN ]

Re:Ask HN: Full-on machine learning for 2020, what are the b... by throwlaplace on Tuesday December 31, 2019 @04:20PM (#21924825)

> Implement their methods from scratch (i.e. numpy not pytorch)

lol this is basically impossible and completely pointless. please show me a numpy implementation of BERT or CycleGAN or deformable convolutions (note that jax != numpy). it's like suggesting implementing a kernel to someone who wants to learn about virtual memory or scheduling.

better advice would be take a paper and implement the model using pytorch without looking at their implementation and fiddle with that.

[ Parent | on HN ]