Articles, learning paths and news on AI, machine learning and data science.
Tutorial series: every part of a topic, in order.
by MLHub Labs · 5 parts · about 89 min · beginner
How computers see, from the first pixel: cameras, colour, OpenCV, filters, edges, masks and video, with three small projects to build on a laptop …
by MLHub Labs · 12 parts · about 281 min · intermediate
How machines see: convolutions, the classic architectures, transfer learning, detection and segmentation.
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
1 day, 12 hours ago • 29 min read
Learn how image filters work by sliding a small grid of numbers over every pixel, and see how box, Gaussian, …
MLHub Deep Learning Organization
1 day, 20 hours ago • 21 min read
Learn how OpenCV represents pictures as NumPy arrays, and master the three basic moves every computer vision script starts with: …
MLHub Deep Learning Organization
2 days, 21 hours ago • 18 min read
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
3 days, 13 hours ago • 24 min read
A new AWS reference architecture tackles a problem that hits factories once a vision inspection pilot succeeds: scaling from one …
The MLHub News Organization
3 days, 20 hours ago • 6 min read
An introduction to a twelve-part project that builds a face-recognising doorbell camera on a Raspberry Pi, and a careful look …
MLHub Deep Learning Organization
4 days, 13 hours ago • 20 min read
A pixel is just three numbers until you decide what they mean. This part explains RGB, greyscale and HSV from …
MLHub Deep Learning Organization
4 days, 21 hours ago • 15 min read
How vision models learn useful representations from unlabeled images alone, through contrastive learning (SimCLR, MoCo, BYOL) and masked image modeling …
MLHub Deep Learning Organization
5 days, 21 hours ago • 22 min read
How the transformer architecture, originally built for text, was adapted to see images by treating them as sequences of patches, …
MLHub Deep Learning Organization
6 days, 21 hours ago • 24 min read
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 ago • 24 min read
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, 1 day ago • 27 min read
Before OpenCV ever touches a photo, light has already been bent by a lens, counted by a sensor and rounded …
MLHub Deep Learning Organization
1 week, 3 days ago • 20 min read
• 6 min read
• 5 min read
• 6 min read
• 6 min read
3 weeks, 4 days ago • 17 min read
0 likes • 117 views • 1 comment
3 days, 20 hours ago • 6 min read
0 likes • 49 views • 0 comments
4 days, 21 hours ago • 15 min read
0 likes • 56 views • 0 comments
Get the latest AI insights and tutorials delivered to your inbox.
Your feedback has been received and we'll review it soon.
