Explore MLHub

Articles, learning paths and news on AI, machine learning and data science.

Clear

Hands-On: Train a YOLO Detector on a Custom Dataset

Computer Vision

Part 13 of 13 · Computer Vision With Convolutional Networks

Hands-On: Train a YOLO Detector on a Custom Dataset

Build a small labeled dataset from scratch, train a YOLOv8 model with the ultralytics library, evaluate it with real detection …

MLHub Deep Learning Organization

23 hours ago • 27 min read

0 0 23

News

NVIDIA's Nemotron 3.5 Super VL Lands on AWS: One Model for Text, Images and Video Agents

NVIDIA has added a 120-billion-parameter multimodal model, Nemotron 3.5 Super VL, to its open Nemotron family, and AWS has published …

The MLHub News Organization

1 day, 22 hours ago • 6 min read

0 0 27

Hands-On: Fine-Tune a ResNet on Your Own Photos

Computer Vision

Part 12 of 13 · Computer Vision With Convolutional Networks

Hands-On: Fine-Tune a ResNet on Your Own Photos

A complete, runnable walkthrough of loading a pretrained ResNet18, replacing its head, fine-tuning it in two phases on an image-folder …

MLHub Deep Learning Organization

2 days, 15 hours ago • 29 min read

0 0 22

News

AWS Publishes a Blueprint for Running AI Agents Safely Across a Whole Company

Amazon Web Services has released a reference architecture that wraps Amazon Bedrock AgentCore in the governance, account isolation and release …

The MLHub News Organization

2 days, 22 hours ago • 5 min read

0 0 30

What a CNN Looks At: Grad-CAM and Saliency

Computer Vision

Part 11 of 13 · Computer Vision With Convolutional Networks

What a CNN Looks At: Grad-CAM and Saliency

A practical guide to opening up convolutional networks with saliency maps and Grad-CAM, so you can see which pixels actually …

MLHub Deep Learning Organization

4 days, 15 hours ago • 24 min read

0 0 39

News

AWS shows how to manage thousands of per-camera vision models with SageMaker SDK v3

A new AWS reference architecture tackles a problem that hits factories once a vision inspection pilot succeeds: scaling from one …

The MLHub News Organization

4 days, 22 hours ago • 6 min read

0 0 68

Deep Learning

What a GPU Does for Deep Learning

A plain-language tour of why graphics cards became the engine of modern AI, covering parallel computation, memory bandwidth, tensor cores …

Niranjan Singh

1 week ago • 13 min read

0 0 11

Computer Vision

Part 9 of 13 · Computer Vision With Convolutional Networks

Vision Transformers

How the transformer architecture, originally built for text, was adapted to see images by treating them as sequences of patches, …

MLHub Deep Learning Organization

1 week, 1 day ago • 24 min read

0 0 57

News

Canva builds its own AI image generator, betting on a 'plan first, draw later' approach

Canva has launched Craft, an in-house image generation model that plans a design before rendering it, aiming to compete with …

The MLHub News Organization

1 week, 1 day ago • 4 min read

0 0 50

Computer Vision

Part 8 of 13 · Computer Vision With Convolutional Networks

Semantic and Instance Segmentation

How neural networks learn to label every pixel in an image, and the difference between painting a scene by category …

MLHub Deep Learning Organization

1 week, 2 days ago • 24 min read

0 0 54

News

AWS Shows How to Mix Small and Large Models in One Agent to Cut Cloud Costs

A new reference architecture from AWS, the Adaptive Agentic Intelligence Framework (AAIF), routes routine AI agent requests to small local …

The MLHub News Organization

1 week, 2 days ago • 5 min read

0 0 50

Object Detection: Anchors, YOLO and DETR

Computer Vision

Part 7 of 13 · Computer Vision With Convolutional Networks

Object Detection: Anchors, YOLO and DETR

How detectors go from a grid of pixels to a list of labelled boxes: the idea of anchors, how YOLO …

MLHub Deep Learning Organization

1 week, 3 days ago • 27 min read

0 0 56

Latest News

All news

Apple Intelligence finally arrives in China, but without the new Siri
22 hours ago • 4 min read
NVIDIA's Nemotron 3.5 Super VL Lands on AWS: One Model for Text, Images and Video Agents
1 day, 22 hours ago • 6 min read
AWS Publishes a Blueprint for Running AI Agents Safely Across a Whole Company
2 days, 22 hours ago • 5 min read
How Exowatt's fine-tuned small models outperformed frontier AI on solar-plant tasks
3 days, 22 hours ago • 6 min read

Recent Activity

MLHub Deep Learning published Edges, Contours and Shapes

15 hours ago
The MLHub News published Apple Intelligence finally arrives in China, but without the new Siri

22 hours ago
MLHub Deep Learning published Hands-On: Train a YOLO Detector on a Custom Dataset

23 hours ago
The MLHub Posts published Ten Data Leakage Mistakes and How to Catch Them

1 day, 15 hours ago
The MLHub News published NVIDIA's Nemotron 3.5 Super VL Lands on AWS: One Model for Text, Imag…

1 day, 22 hours ago
MLHub Agents & Robotics published Hands-On: An Agent in Plain Python, No Framework

2 days ago

Popular Tags

AI agents computer vision data science llm cnn image classification descriptive statist… statistics tool use communication machine learning image processing opencv AI safety AWS

Stay Updated

Get the latest AI insights and tutorials delivered to your inbox.

Load More Articles

Confirm Action

Explore MLHub

Hands-On: Train a YOLO Detector on a Custom Dataset

NVIDIA's Nemotron 3.5 Super VL Lands on AWS: One Model for Text, Images and Video Agents

Hands-On: Fine-Tune a ResNet on Your Own Photos

AWS Publishes a Blueprint for Running AI Agents Safely Across a Whole Company

What a CNN Looks At: Grad-CAM and Saliency

AWS shows how to manage thousands of per-camera vision models with SageMaker SDK v3

What a GPU Does for Deep Learning

Vision Transformers

Canva builds its own AI image generator, betting on a 'plan first, draw later' approach

Semantic and Instance Segmentation

AWS Shows How to Mix Small and Large Models in One Agent to Cut Cloud Costs