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.
G-CARL: Checklist-Aligned Reward Learning for Grounded Medical AI Agents
mech_app_ai profile

G-CARL: Checklist-Aligned Reward Learning for Grounded Medical AI Agents

#agents #ai #llm #machinelearning
Comments
5 min read
Backpropagation by Hand: Two Layers, a Pen, and Then Autograd Agrees
pytorchfromgroundup profile

Backpropagation by Hand: Two Layers, a Pen, and Then Autograd Agrees

#pytorch #python #machinelearning #beginners
Comments
9 min read
Expert-locality-aware decode routing reduces MoE serving latency
olaughter profile

Expert-locality-aware decode routing reduces MoE serving latency

#ai #machinelearning #abotwrotethis
Comments
2 min read
Closed‑loop detection improves attribution accuracy
olaughter profile

Closed‑loop detection improves attribution accuracy

#ai #machinelearning #abotwrotethis
Comments
2 min read
Peer Selection Cuts Regret in Multi‑Agent Coordination
olaughter profile

Peer Selection Cuts Regret in Multi‑Agent Coordination

#ai #machinelearning #abotwrotethis
Comments
2 min read
Skill Entropy reward boosts multi-skill reasoning
olaughter profile

Skill Entropy reward boosts multi-skill reasoning

#ai #machinelearning #abotwrotethis
Comments
2 min read
Uncertainty‑guided distillation improves student efficiency
olaughter profile

Uncertainty‑guided distillation improves student efficiency

#ai #machinelearning #abotwrotethis
Comments
2 min read
I Tested GLM-5.3-Flash and Qwen3.8-Flash on 24 Real Tasks
li_wujie_0995d9c1bca1f2e3 profile

I Tested GLM-5.3-Flash and Qwen3.8-Flash on 24 Real Tasks

#ai #llm #machinelearning #benchmark
Comments
6 min read
Self-Hosted RAG: A Production Pipeline on Your Own Hardware
mryadavgulshan profile

Self-Hosted RAG: A Production Pipeline on Your Own Hardware

#machinelearning
Comments
9 min read
Interpretability Built an Instrument to Prove a Signal Is Actually Used. Agent Memory Has Nothing Like It.
izgorodin profile

Interpretability Built an Instrument to Prove a Signal Is Actually Used. Agent Memory Has Nothing Like It.

#ai #machinelearning #llm #agents
2
Comments
5 min read
Stop Blaming the LLM: Why Your AI Agents Keep Failing (And How to Fix Them)
abdullahahmad profile

Stop Blaming the LLM: Why Your AI Agents Keep Failing (And How to Fix Them)

#ai #programming #productivity #machinelearning
Comments
2 min read
We Taught a 230M Language Model to Keep Learning on Android
ijulin profile

We Taught a 230M Language Model to Keep Learning on Android

#ai #machinelearning #android #opensource
1
Comments
5 min read
What Is AI Inference? The Difference Between Training a Model and Actually Using It
egepakten profile

What Is AI Inference? The Difference Between Training a Model and Actually Using It

#ai #webdev #machinelearning #beginners
Comments
4 min read
From Massive to Miniature: How Small Language Models Are Engineered
chandakvishal profile

From Massive to Miniature: How Small Language Models Are Engineered

#smalllanguagemodel #artificialintelligen #machinelearning #llm
Comments
12 min read
Das System, das sich selbst verbessert
frederikvonderheyden profile

Das System, das sich selbst verbessert

#aiagents #architecture #devops #machinelearning
Comments
4 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.