15 DS/ML Cheat Sheets
Single frame summaries of must-know DS/ML concepts and techniques.
I have published several cheat sheets (or single-frame summary sheets) in this newsletter before.
Today, I am collating them into a single newsletter issue and sharing with you.
Since the cheat sheets are pretty self-explanatory, I won’t provide much details.
Yet, a link to the corresponding issue has been provided for further reference.
Enjoy!
#1) 15 Pandas ↔ Polars ↔ SQL ↔ PySpark Translations
#2) 4 Strategies for Multi-GPU Training
Who likes to stare at a screen during model training? Single-GPU training is rarely desirable if you want to train large models. These four strategies help:
Implementation is available here
#3) 4 Ways to Test ML Models in Production
Instantly replacing an old model with a new one can be a terrible idea. Yet, these are risk-free ways to test the model before replacing the old model:
We covered their implementation here: 5 Must-Know Ways to Test ML Models in Production (Implementation Included).
#4) 15 Ways to Optimize Neural Network Training
Learn what MLEs are actually supposed to do—engineer models, not just train them.
We covered the implementations here: 15 Ways to Optimize Neural Network Training (With Implementation).
#5) Training and Inference Time Complexity of 10 ML Algorithms
Understand whether a particular algorithm is good to proceed with based on your dataset.
#6) 5 LLM Fine-tuning Techniques Explained Visually
Given the scale, traditional fine-tuning does not help in LLMs. These are 5 common strategies:
We covered them in detail here:
#7) NumPy Cheat Sheet Of 40 Most Used Methods
Having used NumPy for years, I can confidently say that you will use these methods 95% of the time working with NumPy.
#8) Most Important Plots in Data Science
#9) Must-know Data Science Glossary
Some of the most common terms that data scientists must know.
#10) 10 Regression and Classification Loss Functions
#11) 11 Types of Variables in a Dataset
#12) 7 Categorical Data Encoding Techniques
#13) 20 Most Common Magic Methods
#14) Full-model Fine-tuning vs. LoRA vs. RAG
#15) Transfer Learning, Fine-tuning, Multitask Learning and Federated Learning
We covered Federated learning in detail with implementation here: Federated Learning: A Critical Step Towards Privacy-Preserving Machine Learning.
That’s a wrap!
👉 Over to you: What more cheat sheets (or single-frame summaries) would you like me to share next?
For those who want to build a career in DS/ML on core expertise, not trends:
Every week, I publish no-fluff deep dives on topics that truly matter to your skills for ML/DS roles.
For instance:
15 Ways to Optimize Neural Network Training (With Implementation)
Conformal Predictions: Build Confidence in Your ML Model’s Predictions
Quantization: Optimize ML Models to Run Them on Tiny Hardware
5 Must-Know Ways to Test ML Models in Production (Implementation Included)
Implementing Parallelized CUDA Programs From Scratch Using CUDA Programming
And many many more.
Join below to unlock all full articles:
SPONSOR US
Get your product in front of ~90,000 data scientists and other tech professionals.
Our newsletter puts your products and services directly in front of an audience that matters — thousands of leaders, senior data scientists, machine learning engineers, data analysts, etc., who have influence over significant tech decisions and big purchases.
To ensure your product reaches this influential audience, reserve your space here or reply to this email to ensure your product reaches this influential audience.