Mark Koh

Expert data Swizzler @Spotify 🎧 Concert photographer 📸 & videographer 🎥

[Mark Tenenholtz @marktenenholtz]

@RAPIDSai To sum it up:

1. Evaluation = speed
2. GPUs everywhere
3. Limit your architectures
4. Kaggle solutions are a DB
5. Refactor more
6. Pipelines > models

I hope you learned something!

Follow me @marktenenholtz to get more high-signal ML content!

[Mark Tenenholtz @marktenenholtz]

I've spent 1000's of hours building ML models over the last couple of years.

Here are some tips that would have made me work 10x faster (that you can read in 2 minutes):

[Mark Koh @markkohdev]

I don't know who needs to hear this, but please use more #dataclasses with type hints in your #python code 🐍 https://t.co/AYD1m4jIfU

[Mark Koh @markkohdev]

Does anyone else do their best thinking when they're at a concert?

[Mark Koh @markkohdev]

@arkosiorek Reinforcement Learning in recommender systems (I'm biased though haha)

[Mark Koh @markkohdev]

@skyetetra

[Mark Tenenholtz @marktenenholtz]

TL;DR:

Tabular: XGBoost/LightGBM/RF
Time series: XGBoost/LightGBM/RF
Image: ResNet/EffNet
Text: RoBERTa
Audio: ResNet/EffNet

Your best bet is usually to start with these and then experiment from there.

Nothing in ML is an end-all-be-all!

[Mark Koh @markkohdev]

In God we trust, all others bring #data.
- William Deming (theoretically)

[Mark Koh @markkohdev]

@wilschroter My parents did this haha, they even called them "play dates"!

[Mark Koh @markkohdev]

...is it too late to start using Twitter?