Tag feed

#deep-learning

2,767 posts1,518 followers

Explore Hashnode

Alternatives

Trending tags this week

ASAnanya Soniananyasoni-aisovereign-agi.hashnode.dev1d ago · 5 min read

I Scrapped My Own Benchmark to Build the Ultimate AGI Lifecycle Engine

It has been just shy of a month—three days short, to be exact—since I dropped the True AGI Sequence Gauntlet. If you read my previous post, you know the promise I made. I told you I was going to rele

0

JSJeevika Slocal-minima.hashnode.dev1d ago · 10 min read

Building an RL Traffic Agent for Indian Roads, Part 8: The Ramp That Wouldn't Go Away

Part 7 ended on a table that looked clean. Nav scaling fixed the steering lock-in, extending training to 100,000 steps gave the CNN room to actually learn road geometry, and every metric in that closi

0

CMChaeyeon Mia Leemiainflorence.hashnode.dev5d ago · 10 min read

The "Understanding Is Done Early" Insight Behind CoMem: A Deep Technical Breakdown

Your GPU runs out of memory at 128k tokens. Your RAG pipeline loses critical context in the middle. You've tried KV cache compression and watched accuracy drop. These aren't configuration problems — t

0

WKWesam Khallafpytorchfromgroundup.hashnode.dev5d ago · 8 min read

PyTorch `permute` vs `transpose`: What's the Difference (and the `reshape` Bug That Scrambles Your Images)

You loaded an image, got a tensor shaped (batch, height, width, channels), and your convolution wants (batch, channels, height, width). Stack Overflow says permute. Someone else says transpose. And re

0

RSRuvarashe Shalom Nemarambaruva.hashnode.dev6d ago · 5 min read

The New ML Perspective

Artificial intelligence seems like a very complex thing packaged in a simple box. It's this magic concept of creating intelligence from something that otherwise wouldn't have any intelligence at all.

0

CMChaeyeon Mia Leemiainflorence.hashnode.dev6d ago · 9 min read

Why GRPO, Dr. GRPO, and DAPO Are All the Same Algorithm in Disguise: The Group-Standard-Deviation Identity

You've spent hours tuning your RLVR training run. GRPO converges too aggressively on hard problems. You switch to Dr. GRPO for stability, but then you read that DAPO gets better results by throwing aw

0

YPYash Piseearlystopping.hashnode.devJul 31 · 35 min read

Early Stopping: Preventing Overfitting for Smarter Machine Learning Models

Learn How Early Stopping Helps Machine Learning Models Generalize Better Instead of Memorizing Training Data Updated: July 31, 2026Estimated Reading Time: 15–18 minutes Introduction Why training your

3

KRP

CMChaeyeon Mia Leemiainflorence.hashnode.devJul 31 · 7 min read

Why Your Sparse Attention Model Is Still Slow at Long Context — and What PIVOT Does Differently

You switched to sparse attention. You followed the DeepSeek-V3.2 architecture. You even tuned your top-k carefully. Yet at 128K context, inference is still painfully slow. The culprit isn't where you

0

PSPrathmesh Sawantfirstmlblog.hashnode.devJul 31 · 8 min read

Loss Landscape Visualization: Understanding How Machine Learning Models Learn

Introduction Machine Learning (ML) has become one of the most influential technologies of the modern era. It powers recommendation systems, self-driving cars, medical diagnosis, virtual assistants, fr

0

JNJoshua Nwachinemerejoshua-nwachinemere.hashnode.devJul 27 · 18 min read

How Computer Vision Learned to See: A Technical History of Where Visual Knowledge Lives

In 2001, Paul Viola and Michael Jones described a face detector that ran at 15 frames per second on 384×288 images using a 700 MHz Pentium III (Viola & Jones, CVPR 2001). That speed was not luck, and

0

#deep-learning

Search Hashnode

#deep-learning

Explore Hashnode

Trending tags this week

I Scrapped My Own Benchmark to Build the Ultimate AGI Lifecycle Engine

Building an RL Traffic Agent for Indian Roads, Part 8: The Ramp That Wouldn't Go Away

The "Understanding Is Done Early" Insight Behind CoMem: A Deep Technical Breakdown

PyTorch `permute` vs `transpose`: What's the Difference (and the `reshape` Bug That Scrambles Your Images)

The New ML Perspective

Why GRPO, Dr. GRPO, and DAPO Are All the Same Algorithm in Disguise: The Group-Standard-Deviation Identity

Early Stopping: Preventing Overfitting for Smarter Machine Learning Models

Why Your Sparse Attention Model Is Still Slow at Long Context — and What PIVOT Does Differently

Loss Landscape Visualization: Understanding How Machine Learning Models Learn

How Computer Vision Learned to See: A Technical History of Where Visual Knowledge Lives