Forem

Deep Learning

This tag is for discussing, sharing articles, and asking questions primarily on deep learning - a subfield of machine learning.

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Deploying a Customer Lifetime Value(CLV) Prediction Model Using FastAPI
Cover image for Deploying a Customer Lifetime Value(CLV) Prediction Model Using FastAPI

Deploying a Customer Lifetime Value(CLV) Prediction Model Using FastAPI

1
Comments
4 min read
I Gave an AI My Study Materials, and It Planned My Entire Learning Schedule. HyperKnow Is Not Just Another Chatbot
Cover image for I Gave an AI My Study Materials, and It Planned My Entire Learning Schedule. HyperKnow Is Not Just Another Chatbot

I Gave an AI My Study Materials, and It Planned My Entire Learning Schedule. HyperKnow Is Not Just Another Chatbot

4
Comments
6 min read
Caching Strategies for LLM Systems (Part 3): Multi-Query Attention and Memory-Efficient Decoding

Caching Strategies for LLM Systems (Part 3): Multi-Query Attention and Memory-Efficient Decoding

Comments
5 min read
vLLM vs TensorRT-LLM vs Ollama vs llama.cpp — Choosing the Right Inference Engine on RTX 5090

vLLM vs TensorRT-LLM vs Ollama vs llama.cpp — Choosing the Right Inference Engine on RTX 5090

1
Comments
7 min read
Building an LLM From Scratch for Indic Languages: What No One Tells You About the Hard Parts
Cover image for Building an LLM From Scratch for Indic Languages: What No One Tells You About the Hard Parts

Building an LLM From Scratch for Indic Languages: What No One Tells You About the Hard Parts

2
Comments
19 min read
Image Augmentation in Practice — Lessons from 10 Years of Training CV Models and Building Albumentations

Image Augmentation in Practice — Lessons from 10 Years of Training CV Models and Building Albumentations

20
Comments 1
30 min read
Deep Learning Without Backpropagation
Cover image for Deep Learning Without Backpropagation

Deep Learning Without Backpropagation

Comments 1
3 min read
Hunting Einstein Rings: Achieving 0.994 mAP in Deep-Space Detection with RT-DETR

Hunting Einstein Rings: Achieving 0.994 mAP in Deep-Space Detection with RT-DETR

2
Comments 1
2 min read
Your Training Data Is Teaching Your Model the Wrong Things
Cover image for Your Training Data Is Teaching Your Model the Wrong Things

Your Training Data Is Teaching Your Model the Wrong Things

2
Comments
3 min read
Multi-head Latent Attention (MLA) — Review

Multi-head Latent Attention (MLA) — Review

Comments
3 min read
The Most Dangerous Number in Machine Learning: Accuracy
Cover image for The Most Dangerous Number in Machine Learning: Accuracy

The Most Dangerous Number in Machine Learning: Accuracy

2
Comments
3 min read
Transformer - Encoder Deep Dive - Part 3: What is Self-Attention

Transformer - Encoder Deep Dive - Part 3: What is Self-Attention

3
Comments 1
9 min read
Understanding the Transformer Architecture : A Student's Journey from Classroom to Exam Hall
Cover image for Understanding the Transformer Architecture : A Student's Journey from Classroom to Exam Hall

Understanding the Transformer Architecture : A Student's Journey from Classroom to Exam Hall

6
Comments 16
10 min read
A New AI Architecture Without Prior Distributions: Stream-Based AI and Compositional Inference

A New AI Architecture Without Prior Distributions: Stream-Based AI and Compositional Inference

Comments
6 min read
ATIC Doesn't Train. It Thinks. — How a Brazilian Developer Hit #1 on LiveBench Without Touching a Single Weight
Cover image for ATIC Doesn't Train. It Thinks. — How a Brazilian Developer Hit #1 on LiveBench Without Touching a Single Weight

ATIC Doesn't Train. It Thinks. — How a Brazilian Developer Hit #1 on LiveBench Without Touching a Single Weight

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