DEV Community

Deep Learning

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

Posts

๐Ÿ‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
๐—ช๐—ต๐—ฎ๐˜ ๐—œ ๐—Ÿ๐—ฒ๐—ฎ๐—ฟ๐—ป๐—ฒ๐—ฑ ๐—ณ๐—ฟ๐—ผ๐—บ ๐—–๐—ต๐—ฎ๐—ฝ๐˜๐—ฒ๐—ฟ ๐Ÿฎ ๐—ผ๐—ณ ๐—”๐—œ ๐—˜๐—ป๐—ด๐—ถ๐—ป๐—ฒ๐—ฒ๐—ฟ๐—ถ๐—ป๐—ด: ๐—ช๐—ต๐˜† ๐—ฆ๐—ฎ๐—บ๐—ฝ๐—น๐—ถ๐—ป๐—ด ๐—–๐—ต๐—ฎ๐—ป๐—ด๐—ฒ๐˜€ ๐—˜๐˜ƒ๐—ฒ๐—ฟ๐˜†๐˜๐—ต๐—ถ๐—ป๐—ด

๐—ช๐—ต๐—ฎ๐˜ ๐—œ ๐—Ÿ๐—ฒ๐—ฎ๐—ฟ๐—ป๐—ฒ๐—ฑ ๐—ณ๐—ฟ๐—ผ๐—บ ๐—–๐—ต๐—ฎ๐—ฝ๐˜๐—ฒ๐—ฟ ๐Ÿฎ ๐—ผ๐—ณ ๐—”๐—œ ๐—˜๐—ป๐—ด๐—ถ๐—ป๐—ฒ๐—ฒ๐—ฟ๐—ถ๐—ป๐—ด: ๐—ช๐—ต๐˜† ๐—ฆ๐—ฎ๐—บ๐—ฝ๐—น๐—ถ๐—ป๐—ด ๐—–๐—ต๐—ฎ๐—ป๐—ด๐—ฒ๐˜€ ๐—˜๐˜ƒ๐—ฒ๐—ฟ๐˜†๐˜๐—ต๐—ถ๐—ป๐—ด

1
Comments
4 min read
Blog 2: Momentum-Based Optimizers

Blog 2: Momentum-Based Optimizers

Comments
6 min read
Blog 1: Foundations of Gradient Descent

Blog 1: Foundations of Gradient Descent

Comments
5 min read
I Built the World's First AI Knowledge Arena โ€” Battle Other Devs on ML & Deep Learning

I Built the World's First AI Knowledge Arena โ€” Battle Other Devs on ML & Deep Learning

Comments
3 min read
Policy Gradients: REINFORCE from Scratch with NumPy

Policy Gradients: REINFORCE from Scratch with NumPy

Comments
16 min read
Why does paying more make your LLM reply faster?

Why does paying more make your LLM reply faster?

2
Comments 2
3 min read
2 Lines of Code Saved 6.4x Memory on My Snake AI

2 Lines of Code Saved 6.4x Memory on My Snake AI

3
Comments
6 min read
Replace Claude Code's Context-Stuffing with git-semantic for Team-Wide Semantic Search

Replace Claude Code's Context-Stuffing with git-semantic for Team-Wide Semantic Search

Comments
3 min read
Image Prompt Packaging Cuts Multimodal Inference Costs Up to 91%

Image Prompt Packaging Cuts Multimodal Inference Costs Up to 91%

Comments
6 min read
Decoding Base Model Readiness for Downstream Tasks

Decoding Base Model Readiness for Downstream Tasks

Comments
1 min read
AIโ€™s Biggest Problem Isnโ€™t Intelligence โ€” Itโ€™s Evaluation

AIโ€™s Biggest Problem Isnโ€™t Intelligence โ€” Itโ€™s Evaluation

Comments
6 min read
Deep Q-Networks: Experience Replay and Target Networks

Deep Q-Networks: Experience Replay and Target Networks

Comments
18 min read
AI News This Week: April 6, 2026 - Autonomous Driving, Token Efficiency, and More

AI News This Week: April 6, 2026 - Autonomous Driving, Token Efficiency, and More

Comments
4 min read
I Rebuilt Karpathy's NanoChat in JAX. Here's What XLA Gets Right and What It Gets Dead Wrong.

JIT error detection vs silent gradient bugs

I Rebuilt Karpathy's NanoChat in JAX. Here's What XLA Gets Right and What It Gets Dead Wrong.

22
Comments 6
13 min read
I Built A Monster Model Before I Built a Working One

I Built A Monster Model Before I Built a Working One

Comments
4 min read
๐Ÿ‘‹ Sign in for the ability to sort posts by relevant, latest, or top.