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.
Fine-Tuning Transformers Vs Lora Vs Qlora 2024

Fine-Tuning Transformers Vs Lora Vs Qlora 2024

Comments
6 min read
I Spent a Year Building an AI Verification Framework. Then I Found a Hole.

I Spent a Year Building an AI Verification Framework. Then I Found a Hole.

Comments
4 min read
Rag Evaluation Metrics

Rag Evaluation Metrics

Comments
6 min read
Real-time detection of vertical tongue movements via mobile camera — looking for the right approach

Real-time detection of vertical tongue movements via mobile camera — looking for the right approach

Comments
1 min read
Physical AI just got its platform layer. Nvidia is the only candidate. Here's what you missed this week.

Physical AI just got its platform layer. Nvidia is the only candidate. Here's what you missed this week.

Comments
6 min read
Sampling strategies compared: temperature, top-p, top-k, min-p, and what actually works in production

Sampling strategies compared: temperature, top-p, top-k, min-p, and what actually works in production

Comments
9 min read
Benchmarks Evaluate Memory Quality and Adaptive Planning in LLM Agents

Benchmarks Evaluate Memory Quality and Adaptive Planning in LLM Agents

Comments
3 min read
Follow-Up: Decision-Token Measurement, Format-as-Fallback, and What Changed

Frozen annotations to avoid lookback bias

Follow-Up: Decision-Token Measurement, Format-as-Fallback, and What Changed

3
Comments 14
4 min read
The Missing Piece in Jason Wei's Framework: When to Go On-Policy

The Missing Piece in Jason Wei's Framework: When to Go On-Policy

Comments
4 min read
Wiring DeepSeek Into Your NestJS Stack: A Backend Walkthrough

Wiring DeepSeek Into Your NestJS Stack: A Backend Walkthrough

1
Comments
8 min read
From A10 to M60: An Architect's Journey into Azure GPU VM Sizing for Kubernetes Inference Workloads

From A10 to M60: An Architect's Journey into Azure GPU VM Sizing for Kubernetes Inference Workloads

1
Comments 2
4 min read
GPT-5.5, Codex GA on Bedrock; MiMo Code Open-Source; Claude Fable Guardrail Apology

GPT-5.5, Codex GA on Bedrock; MiMo Code Open-Source; Claude Fable Guardrail Apology

Comments
3 min read
From Pilots to Production: A Practical AI Playbook for Credit Unions

From Pilots to Production: A Practical AI Playbook for Credit Unions

Comments
7 min read
Why Chasing Every New Frontier Model is Breaking Your Focus

Why Chasing Every New Frontier Model is Breaking Your Focus

Comments 2
4 min read
Building a Korea-Market Middleware for Microsoft Qlib

Building a Korea-Market Middleware for Microsoft Qlib

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