Can you reverse engineer our neural network?
A lot of “capture-the-flag” style ML puzzles give you a black box neural net, and your job is to figure out what it does. When we were thinking of creating our own ML puzzle early last year, we…
Read the full articleYou might also wanna read
Demystifying the Training of Two-Layer Neural Networks
Exploring the mysteries of two-layer neural networks, a new method reveals how back-propagation untangles the 'black box.' But is it truly g
Cracking Neural Networks: A Deeper Dive Into Mechanistic Interpretability
Mechanistic interpretability aims to unravel the complex inner workings of neural networks. By breaking down these 'black boxes,' the field
Cracking the Code: Making Sense of Neural Network Weights
Understanding neural networks isn't just about complex math. Recent findings suggest that a significant portion of weights in sparse transfo
The surprising structural similarities between neural networks and cryptographic ciphers
Several neural network design principles are almost identical to cipher design principles.
Reiner’s webpage and articles.·2mo agoHow to Build Neural Networks from Scratch with PyTorch: A Step-by-Step Guide
Neural networks are fascinating constructs often credited as being “inspired by the brain.” Yet, what does that really mean in terms of code
Understanding Transformer Circuits: A Mechanistic Interpretability Perspective
A mental model for addressing the residual stream
connorjdavis.com·3mo ago
Comments
Sign in to join the conversation.
No comments yet. Be the first.