DEV Community

Machine Learning

A branch of artificial intelligence (AI) and computer science which focuses on the use of data and algorithms to imitate the way that humans learn, gradually improving its accuracy.

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Better Data Beats Better Algorithms: Before Changing the Model, Change the Data

Better Data Beats Better Algorithms: Before Changing the Model, Change the Data

Comments
3 min read
The regression your eval set is too small to catch

The regression your eval set is too small to catch

1
Comments 2
7 min read
NeuraDebugger-Micro-1.1B: The 1B Parameter Debugging Specialist That Outperforms Generalists

NeuraDebugger-Micro-1.1B: The 1B Parameter Debugging Specialist That Outperforms Generalists

Comments
9 min read
Understanding Attention in Transformers — Intuition Before Equations

Understanding Attention in Transformers — Intuition Before Equations

Comments
3 min read
How We Stopped Losing 45 Minutes Every Time Production Broke

How We Stopped Losing 45 Minutes Every Time Production Broke

Comments
5 min read
Even BlackRock stopped trusting a single AI model. Retail traders should take the hint.

Even BlackRock stopped trusting a single AI model. Retail traders should take the hint.

Comments
5 min read
LLMs are Demented!

Interactive crossword on hardware limits

LLMs are Demented!

33
Comments 22
3 min read
Gemma 4 Local Inference with LiteRT-LM, LinkedIn's AI Agent Patterns, Securing AI Stack

Gemma 4 Local Inference with LiteRT-LM, LinkedIn's AI Agent Patterns, Securing AI Stack

Comments
4 min read
XGBoost: the gradient boosting that dominated Kaggle and survived the hype

XGBoost: the gradient boosting that dominated Kaggle and survived the hype

1
Comments 1
5 min read
AI Agents Can't Self-Verify — And That's a Structural Constraint, Not a Bug

AI Agents Can't Self-Verify — And That's a Structural Constraint, Not a Bug

Comments
3 min read
Look-ahead bias is quietly breaking your AI agent backtests

Look-ahead bias is quietly breaking your AI agent backtests

Comments
2 min read
Taxonomy Surgery, Cosine = 1.0000, and Making Routing Disappear into Infrastructure

Taxonomy Surgery, Cosine = 1.0000, and Making Routing Disappear into Infrastructure

3
Comments
5 min read
How Spotify Streams Audio and Builds Discover Weekly

How Spotify Streams Audio and Builds Discover Weekly

Comments
3 min read
Building a Financial Risk Intelligence Agent That Learns from Every Investigation

Building a Financial Risk Intelligence Agent That Learns from Every Investigation

1
Comments
5 min read
Teaching a Reranker the Language of Security Tickets (+41% MRR@10)

Teaching a Reranker the Language of Security Tickets (+41% MRR@10)

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