
Batch, Stochastic, and Mini-Batch Gradient Descent: What's Actually Different
Part 13 of my "revisiting my AI/ML notes" series. Every post in this series so far used gradient...
Tag archive

Part 13 of my "revisiting my AI/ML notes" series. Every post in this series so far used gradient...

Part 6 of my "revisiting my AI/ML notes" series. Everything so far in this series used a single...

"모델이 학습한다"의 안에서 무엇이 일어나는지 한 번도 안 들여다보면 머신러닝이 신비로 남습니다. 손실 함수·gradient descent의 한 줄 직관 — "오차를 어떻게 줄이나" — 만 잡으면 회귀·분류·딥러닝이 같은 원리로 보입니다.
When one learning rate isn't enough — per-parameter scaling and the decay...

Want to get a real feel for machine learning in practice? Here’s a simple but powerful exercise:...
Giving the optimizer a memory — and teaching it to look before it leaps SGD knows where...
How neural networks learn — and why the obvious approach breaks immediately Every...

This exercise shows the basics of the Linear Regression algorithm using: MSE and Gradient...

The gradient descent algorithm is an approach to find the minimum point or optimal solution for a giv...

Gradient Descent in Linear Regression Gradient Descent is a first order optimization algor...
Understand Linear Regression algorithm using gradient descent with minimum pre-knowledge. Get intuition on how it works, how math comes together and how to do a simple implementation