DEV Community

Deep Learning

This tag is for discussing, sharing articles, and asking questions primarily on deep learning - a subfield of machine learning.

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
GRPO, Dr. GRPO, and DAPO Explained — The One Identity That Unifies All Three

GRPO, Dr. GRPO, and DAPO Explained — The One Identity That Unifies All Three

Comments
5 min read
PyTorch `permute` vs `transpose`: What's the Difference (and the `reshape` Bug That Scrambles Your Images)

PyTorch `permute` vs `transpose`: What's the Difference (and the `reshape` Bug That Scrambles Your Images)

Comments
7 min read
First Commit of Machine Learning

First Commit of Machine Learning

Comments
2 min read
I Implemented the Algorithm Behind ChatGPT From Scratch - Day 8 (PPO).

I Implemented the Algorithm Behind ChatGPT From Scratch - Day 8 (PPO).

11
Comments
3 min read
From Learning Machine Learning to Competing on Kaggle: My First End-to-End Playground Competition Journey

From Learning Machine Learning to Competing on Kaggle: My First End-to-End Playground Competition Journey

Comments
9 min read
Separar canciones en stems con HTDemucs v4 en un servidor con poca RAM

Separar canciones en stems con HTDemucs v4 en un servidor con poca RAM

Comments
2 min read
Detecting Objects in Satellite Imagery with YOLOv8: xView + DOTA to YOLO in Practice

Detecting Objects in Satellite Imagery with YOLOv8: xView + DOTA to YOLO in Practice

1
Comments 3
5 min read
权重即数据:神经网络权重空间学习如何成为 AI 的下一类训练集

权重即数据:神经网络权重空间学习如何成为 AI 的下一类训练集

Comments
2 min read
The Evolution of AI, Explained in Stages

The Evolution of AI, Explained in Stages

Comments 1
3 min read
How Vision-Language Models Learned to Reason About Space (10 Papers, One Thread)

How Vision-Language Models Learned to Reason About Space (10 Papers, One Thread)

Comments
3 min read
MoE Capacity Factor: Why Mixture-of-Experts Drops Your Tokens

MoE Capacity Factor: Why Mixture-of-Experts Drops Your Tokens

Comments
8 min read
I Taught an Agent to Act Directly - No Q-Values Needed (Day 6: REINFORCE)

I Taught an Agent to Act Directly - No Q-Values Needed (Day 6: REINFORCE)

5
Comments
3 min read
Building Your Own Deep Learning Framework: A 3–5 Month Journey From Zero to Tiny Transformer

Building Your Own Deep Learning Framework: A 3–5 Month Journey From Zero to Tiny Transformer

Comments
28 min read
I Finally Understood Why Neural Networks Need Activation Functions

I Finally Understood Why Neural Networks Need Activation Functions

Comments
3 min read
Deep Learning Libraries for Beginners: A Comparative Overview

Deep Learning Libraries for Beginners: A Comparative Overview

1
Comments
6 min read
👋 Sign in for the ability to sort posts by relevant, latest, or top.