DEV Community

Deep Learning

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

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
The Guardrails Paradox: Why Constraint Is What Lets AI Move Fast

The Guardrails Paradox: Why Constraint Is What Lets AI Move Fast

Comments
8 min read
FeliniAI: un triple pipeline (visiĂłn + clĂ­nico + LLM) para detectar alergias felinas con F1 0.97

FeliniAI: un triple pipeline (visiĂłn + clĂ­nico + LLM) para detectar alergias felinas con F1 0.97

Comments
2 min read
GPU vs CPU for AI: Why GPUs Win for Many Workloads and When CPUs Still Matter

GPU vs CPU for AI: Why GPUs Win for Many Workloads and When CPUs Still Matter

Comments
13 min read
Beyond Size: The Three Pillars of Test-Time Scaling in Large Language Models

Beyond Size: The Three Pillars of Test-Time Scaling in Large Language Models

Comments
5 min read
Decoupling Physical Control and Reasoning: DeepMind's Gemini Robotics 2 Architecture

Decoupling Physical Control and Reasoning: DeepMind's Gemini Robotics 2 Architecture

Comments
5 min read
GEPA Explained — From Paper to Working Code in 10 Minutes

GEPA Explained — From Paper to Working Code in 10 Minutes

Comments
5 min read
CoMem Explained — From Paper to Working Code in 10 Minutes

CoMem Explained — From Paper to Working Code in 10 Minutes

Comments
6 min read
Four Mechanisms Were Blamed for Loss Spikes in 2026. We Tested All Four at Once. None of Them Alone Causes Spikes.

Four Mechanisms Were Blamed for Loss Spikes in 2026. We Tested All Four at Once. None of Them Alone Causes Spikes.

Comments 1
3 min read
The Invisible Complexity Behind Simple Human Actions: Why Teaching Machines What We Do Naturally Is So Hard

The Invisible Complexity Behind Simple Human Actions: Why Teaching Machines What We Do Naturally Is So Hard

Comments
2 min read
Inverse Problems: Why Predicting Backward Is Harder Than It Looks

Inverse Problems: Why Predicting Backward Is Harder Than It Looks

Comments
6 min read
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
Every Greedy Metric Said the Model Was Improving. Then pass@64 Fell From 0.83 to 0.19

Every Greedy Metric Said the Model Was Improving. Then pass@64 Fell From 0.83 to 0.19

1
Comments
5 min read
Neve - Towards a Unified Programming Model for the Complete Deep Learning Stack

Neve - Towards a Unified Programming Model for the Complete Deep Learning Stack

Comments 1
8 min read
First Commit of Machine Learning

First Commit of Machine Learning

Comments
2 min read
AI Scalability - A Systems Engineer's Guide

AI Scalability - A Systems Engineer's Guide

Comments 1
8 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.