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.
Variance Testing in Forecasting

Variance Testing in Forecasting

Comments
5 min read
AI Hiring Automation Ethics

AI Hiring Automation Ethics

1
Comments
4 min read
Transformer Attention Is Hopfield's 1982 Update Rule (And What That Tells Us About LLM Memory)

Transformer Attention Is Hopfield's 1982 Update Rule (And What That Tells Us About LLM Memory)

2
Comments 2
7 min read
Notes on Serving LLMs with TensorRT-LLM and Triton

Notes on Serving LLMs with TensorRT-LLM and Triton

Comments
4 min read
Making RNNs Actually Work: LSTMs, Bidirectionality, and the Encoder-Decoder

Making RNNs Actually Work: LSTMs, Bidirectionality, and the Encoder-Decoder

Comments
15 min read
What secretly eats your local LLMs' speed as your context fills up - Part 2

What secretly eats your local LLMs' speed as your context fills up - Part 2

1
Comments
4 min read
I tried to hide semantic meaning from embeddings without breaking search

I tried to hide semantic meaning from embeddings without breaking search

Comments
3 min read
Why I Generated Synthetic Patients to Make Identity Matching Better

Why I Generated Synthetic Patients to Make Identity Matching Better

Comments
5 min read
Your AI Agents Are Failing Silently — Here's How to Catch It

Your AI Agents Are Failing Silently — Here's How to Catch It

2
Comments 1
2 min read
The Real Architecture Behind AI Entertainment: Latency, Provenance, and Cost-Per-Minute

The Real Architecture Behind AI Entertainment: Latency, Provenance, and Cost-Per-Minute

1
Comments
4 min read
Where Tensor-Parallel Inference Hits the NVLink Wall

Where Tensor-Parallel Inference Hits the NVLink Wall

Comments
2 min read
Hallucinations Are Not Always Wrong Facts: Sometimes They're Wrong Interpretations

Hallucinations Are Not Always Wrong Facts: Sometimes They're Wrong Interpretations

1
Comments 1
2 min read
Building my humanoid robot

Building my humanoid robot

7
Comments 2
13 min read
Demystifying Deep Learning Optimization: From Feature Scaling to Adam and Beyond

Demystifying Deep Learning Optimization: From Feature Scaling to Adam and Beyond

Comments
7 min read
Microsoft MAI-Code-1-Flash: Adaptive Solution-Length Control

Microsoft MAI-Code-1-Flash: Adaptive Solution-Length Control

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