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.
The Architecture of Generation: Understanding Diffusion Transformers (DiTs)

The Architecture of Generation: Understanding Diffusion Transformers (DiTs)

Comments
2 min read
What if every dial had its own step size?

What if every dial had its own step size?

Comments
4 min read
Why slow down near the finish line?

Why slow down near the finish line?

Comments
5 min read
Platonic Representation Hypothesis becomes a theorem for JEPAs in new arXiv paper

Platonic Representation Hypothesis becomes a theorem for JEPAs in new arXiv paper

Comments
3 min read
Proximal Methods: Why Splitting a Nonsmooth Problem Beats Solving It Directly

Proximal Methods: Why Splitting a Nonsmooth Problem Beats Solving It Directly

Comments
7 min read
DeepSeek Super-agent: A Proactive Open-Source Coding Agent Prototype — What It Actually Is, and What It Is Not Yet

DeepSeek Super-agent: A Proactive Open-Source Coding Agent Prototype — What It Actually Is, and What It Is Not Yet

Comments
3 min read
Distributional Reinforcement Learning: Why Predicting a Distribution Beats Predicting a Mean

Distributional Reinforcement Learning: Why Predicting a Distribution Beats Predicting a Mean

Comments
10 min read
How does a rolling ball skip small bumps?

How does a rolling ball skip small bumps?

Comments 1
5 min read
How do you find a valley blindfolded?

How do you find a valley blindfolded?

Comments
5 min read
Why train on a few examples at a time?

Why train on a few examples at a time?

Comments
5 min read
How does PyTorch find every gradient by itself?

How does PyTorch find every gradient by itself?

Comments
5 min read
Who's to blame when a network gets it wrong?

Who's to blame when a network gets it wrong?

Comments
6 min read
How does one nudge ripple through ten layers?

How does one nudge ripple through ten layers?

Comments
5 min read
Too big, it explodes. Too small, it crawls.

Too big, it explodes. Too small, it crawls.

Comments 1
5 min read
This is what a confident mistake looks like

This is what a confident mistake looks like

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