ML topics I love exploring

Jan 21, 202521 min read

Visualizing the Activation, Gradients, Gradient to data ratio, and Update to Data Distributions in Neural Networks Training.

In my last three blog posts, we explained about how to reduce the wrong but high confidence of neural network, how to identify dead neurons, and The Kaiming initialization and batch normalization. The core of these three blog post is, the correct ini...

The Kaiming initialization and Batch Normalization in Neural Networks
Jan 7, 202517 min read
Identifying and Removing Dead Neurons in Training Neural Networks: Mechanistic Interpretability Part 2
Dec 30, 20249 min read
How to correctly Initialize the Neural Network: Mechanistic Interpretability Part 1
Dec 20, 20249 min read
Training a Basic Language Model (Trigram Language Model)
Sep 17, 202413 min read

How basic concept of Calculus (Derivative) has a Key Role in Training Neural Networks?
A Neural Network is a machine learning model that works like the human brain. Just like how our brain has neurons that send signals, a neural network has artificial neurons that pass information. The network takes input, does some math, and passes th...
Sep 4, 20249 min read

ML topics I love exploring

Latest articles

Visualizing the Activation, Gradients, Gradient to data ratio, and Update to Data Distributions in Neural Networks Training.

The Kaiming initialization and Batch Normalization in Neural Networks

Identifying and Removing Dead Neurons in Training Neural Networks: Mechanistic Interpretability Part 2

How to correctly Initialize the Neural Network: Mechanistic Interpretability Part 1

Training a Basic Language Model (Trigram Language Model)

How basic concept of Calculus (Derivative) has a Key Role in Training Neural Networks?