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.
My first trading models knew which companies would survive

My first trading models knew which companies would survive

1
Comments 5
19 min read
Multi-Reward RL, Part 2: Benchmarking GRPO, DAPO, and CISPO on Unseen Tasks

Multi-Reward RL, Part 2: Benchmarking GRPO, DAPO, and CISPO on Unseen Tasks

1
Comments
11 min read
LLM Inference Optimization: Techniques for Faster and Cheaper AI

LLM Inference Optimization: Techniques for Faster and Cheaper AI

Comments
2 min read
E se uma IA pudesse prever riscos em um carro de FĂłrmula 1 antes do acidente?

E se uma IA pudesse prever riscos em um carro de FĂłrmula 1 antes do acidente?

Comments
5 min read
Practice RAG Retrieval Metrics Offline — A Tiny Stdlib Eval Loop (Synthetic Data)

Practice RAG Retrieval Metrics Offline — A Tiny Stdlib Eval Loop (Synthetic Data)

Comments 2
5 min read
AI Model Versioning and Rollback Strategies for Production

AI Model Versioning and Rollback Strategies for Production

Comments
4 min read
DeepSeek MLA Architecture: How Multi-Head Latent Attention Cuts KV Cache by 93%

DeepSeek MLA Architecture: How Multi-Head Latent Attention Cuts KV Cache by 93%

1
Comments 1
9 min read
Gemma 4 Inference on AWS: Bedrock, SageMaker, GPUs, Inferentia and Trainium Behind One Strands Agent

Gemma 4 Inference on AWS: Bedrock, SageMaker, GPUs, Inferentia and Trainium Behind One Strands Agent

1
Comments 3
13 min read
Ai Voice Analysis

Ai Voice Analysis

Comments 1
9 min read
Stop Asking Your AI to Be Helpful. Ask It to Be Accountable.

Stop Asking Your AI to Be Helpful. Ask It to Be Accountable.

Comments
3 min read
Neural Networks Explained: From Inspiration to Implementation

Neural Networks Explained: From Inspiration to Implementation

Comments
10 min read
Google's QAT Gemma 4 26B-A4B on One TPU v6e: 15.6x the KV Cache and 1.9x the Throughput of FP8

Google's QAT Gemma 4 26B-A4B on One TPU v6e: 15.6x the KV Cache and 1.9x the Throughput of FP8

Comments 1
12 min read
Part 9: Watch and Learn

Part 9: Watch and Learn

1
Comments
5 min read
Joint weight‑harness optimization approaches fine‑tuned model performance

Joint weight‑harness optimization approaches fine‑tuned model performance

Comments
2 min read
AWQ Looked 10 Points Better on GSM8K Until I Stopped Truncating the Answers

AWQ Looked 10 Points Better on GSM8K Until I Stopped Truncating the Answers

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