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.
How Model Distillation Actually Works (and What the 'China Distilled Our Model' Headlines Really Mean)

How Model Distillation Actually Works (and What the 'China Distilled Our Model' Headlines Really Mean)

4
Comments
6 min read
Andrej Karpathy's Neural Networks: Zero to Hero — 1) Intro to Neural Networks and Backpropagation

Andrej Karpathy's Neural Networks: Zero to Hero — 1) Intro to Neural Networks and Backpropagation

Comments
9 min read
✨📊 🧠 The Ultimate Visual Guide to Large Language Models (LLMs)

✨📊 🧠 The Ultimate Visual Guide to Large Language Models (LLMs)

5
Comments
4 min read
I Was Spending $3,200/Month on GPT. Then I Tried Chinese Models.

I Was Spending $3,200/Month on GPT. Then I Tried Chinese Models.

Comments
3 min read
GPT-5.5: OpenAI Admits Decline. The AI Reality Check.

GPT-5.5: OpenAI Admits Decline. The AI Reality Check.

Comments
9 min read
Deep Learning for Beginners: A Complete Guide

Deep Learning for Beginners: A Complete Guide

Comments
12 min read
How Neural Networks Actually Work — A Thread for Curious Minds

How Neural Networks Actually Work — A Thread for Curious Minds

Comments
2 min read
Time When More Layers Meant Worse Model ... Birth Of Residual

Time When More Layers Meant Worse Model ... Birth Of Residual

1
Comments
6 min read
When Preprocessing Helps-and When It Hurts: Why Your Image Classification Model's Accuracy Varies So Much

When Preprocessing Helps-and When It Hurts: Why Your Image Classification Model's Accuracy Varies So Much

1
Comments
14 min read
VLA or IL? A Controlled Dataset for Testing Whether Finetuning Turns Your VLA into a Fancy Imitation Learner

VLA or IL? A Controlled Dataset for Testing Whether Finetuning Turns Your VLA into a Fancy Imitation Learner

Comments
5 min read
114 pages of ML math, and what actually shows up at work

114 pages of ML math, and what actually shows up at work

Comments
4 min read
AlphaEarth Satellite Embeddings : révolution ou gadget pour l’exploration minière ?

AlphaEarth Satellite Embeddings : révolution ou gadget pour l’exploration minière ?

1
Comments
6 min read
Thinking as Compression: How CoLaR Shrinks LLM Reasoning Chains

Thinking as Compression: How CoLaR Shrinks LLM Reasoning Chains

Comments
5 min read
Transformers & Agile Sprints: The Art of Incremental Evolution

Transformers & Agile Sprints: The Art of Incremental Evolution

Comments
2 min read
AlphaEvolve: Google DeepMind's Gemini-Powered Evolutionary Coding Agent

AlphaEvolve: Google DeepMind's Gemini-Powered Evolutionary Coding Agent

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