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.
Backtest 63.7%, production AUC 0.51 - a postmortem
khavel profile
Khavel

Backtest 63.7%, production AUC 0.51 - a postmortem

#showdev #machinelearning #datascience #mlops
Comments
3 min read
The Verification Gap: We Automated Code Generation and Forgot to Scale Review
james-coombs profile

The Verification Gap: We Automated Code Generation and Forgot to Scale Review

#ai #programming #machinelearning #productivity
1
Comments 4
7 min read
I Asked 11 AI Models to Predict My Race Splits. Once I Named the Race, 5 Clearly Beat My Model

Kaggle Benchmarking Challenge Submission
iamrobertmoore profile

I Asked 11 AI Models to Predict My Race Splits. Once I Named the Race, 5 Clearly Beat My Model

#devchallenge #kagglechallenge #ai #machinelearning
3
Comments 1
16 min read
How to Build a Good Human-in-the-Loop for Machine Learning
brennhill profile

How to Build a Good Human-in-the-Loop for Machine Learning

#ai #machinelearning #datascience #llm
2
Comments 3
8 min read
GPT-6 Astra Isn't AGI. It's a For-Loop With Better PR
ashraf_chowdury09 profile

GPT-6 Astra Isn't AGI. It's a For-Loop With Better PR

#ai #machinelearning #opinion #programming
Comments 1
5 min read
Demystifying LLM Context Windows: How AI Memory Works (and Why It Fails)
iar01 profile

Demystifying LLM Context Windows: How AI Memory Works (and Why It Fails)

#ai #llm #rag #machinelearning
Comments
7 min read
Agent Memory Is Not a Vector Database. It's a Forgetting System.
lovakush profile

Agent Memory Is Not a Vector Database. It's a Forgetting System.

#ai #llm #machinelearning #architecture
1
Comments 1
7 min read
"RoPE extrapolates to longer contexts" — someone finally measured it, and it doesn't
narotra05hp profile

"RoPE extrapolates to longer contexts" — someone finally measured it, and it doesn't

#ai #machinelearning #llm #computerscience
Comments 1
3 min read
How I Built a 150 GB Multilingual & Code Dataset for Central Asian AI (And Fought Out-of-Memory Errors for 10 Hours)
fortaki_98f88e7727c326657 profile

How I Built a 150 GB Multilingual & Code Dataset for Central Asian AI (And Fought Out-of-Memory Errors for 10 Hours)

#ai #llm #machinelearning #opensource
2
Comments 1
2 min read
A retry decision was enough to close the first factory loop
sarthakagrawal927 profile

A retry decision was enough to close the first factory loop

#machinelearning #ai #opensource #devlog
Comments
1 min read
Machine Learning for Customer Churn Prediction: What Actually Works
rwaltzsoftware profile

Machine Learning for Customer Churn Prediction: What Actually Works

#analytics #datascience #machinelearning
Comments 1
5 min read
What decision models can't do: six honest limits
mrsaynothing profile

What decision models can't do: six honest limits

#discuss #ai #ollama #machinelearning
5
Comments 13
3 min read
From API to GPU, Week 6 (Part 1): A Model That Predicts, and How Wrong It Is
dramasamy profile

From API to GPU, Week 6 (Part 1): A Model That Predicts, and How Wrong It Is

#ai #llm #gpu #machinelearning
Comments
13 min read
From API to GPU, Week 6 (Part 2): Watching a Neural Network Learn
dramasamy profile

From API to GPU, Week 6 (Part 2): Watching a Neural Network Learn

#ai #llm #gpu #machinelearning
Comments
17 min read
Infino: fastest VectorDB at a million, still cheaper at a billion
muralikpbhat profile

Infino: fastest VectorDB at a million, still cheaper at a billion

#vectordatabase #rag #ai #machinelearning
1
Comments
9 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.