The arc prize problems are visual – naturally they encounter similar situations that visual editors do. Q: Taken a shape, can you flood fill it? Q: Can you take a shape and transform it by a consistent transform – scaling? Q: Can you take a shape and transform it by a relative transform – relative…
All posts in Machine Learning
Django and pgvector for semantic search
Goal: Semantic Search Setup pgvector You have a model with a field you want to make semantically searchable. Installation comes from: https://github.com/pgvector/pgvector-python Step: install pgvector on your machine Step: create a migration to activate Step: add a VectorField to your model Step: make migrations and migrate Setup sentence transformers for embeddings We will use the…
Can ChatGPT do math? NO! But why?
ChatGPT can “kind of” do math, but with limited precision. 1+1, 2+2, it’s great at these additions. Here’s GPT-3.5 Here’s GPT-4 But why? Interestingly, GPT knows the way it was trained and the inherent limitations of using a language model to produce accurate arithmetic.
GPT from scratch: Karpathy
Andrej Karpathy has an incredible video on building GPT from scratch. Here are cartoon notes covering the contents:
Cartoons for Machine Learning Coursera Andrew Ng: Week 1-5 V2
This is an updated and improved version of the original “AI Cartoons” from here (https://theptrk.com/2020/07/05/machine-learning-coursera-week-1-illustrations/). I love drawing these cartoons because it helps solidify the fundamentals and play with concepts in my mind. AI-Cartoons-Weeks-1-5-V2.pdf If you have feedback, I would love to chat on Discord here Thanks for Andrew Ng who sparked the interest in…
Machine Learning Coursera Andrew Ng: Week 1 Illustrations
The Machine Learning course from Coursera with Andrew Ng is the best introduction to Machine Learning on the internet. These illustrated notes are from taking the course and letting the concepts solidify in my thoughts. Please enjoy.
Machine Learning Introduction: My three favorite resources
My three favorite introductory resources to Machine Learning “Machine Learning” Coursera course by Andrew Ng (link) This is the canonical best introduction to machine learning. It’s recommended by most and is a top choice for introduction to ML even in some FAANG some companies. The course covers supervised learning (including linear regression and logistic regression…
Understanding Dimensions – Linear, Logistic Regression
In the forums of the Coursera course “Machine Learning” by Andrew Ng, there are many questions regarding the dimensions of the input matrix and theta. Here is an intuitive guide to understanding the dimensions. Click the link below! Understanding-Dimensions-Linear-Logistic-Regression.pdf In Summary: The dimensions of your input matrix (X) is typically clear and driven from…
Notes for Coursera Machine Learning Course with Andrew Ng (Week 1-5)
I am currently taking the Machine Learning Coursera course by Andrew Ng and I’m loving it! I’ve started compiling my notes in handwritten and illustrated form and wanted to share it here. If you are taking the course you can follow along 🙂 AI Cartoons Week 1 – 5 (PDF download link) Sign up for…