A tutorial on building a Sudoku solver application using Azure Form Recognizer AI, .NET backend, and Angular frontend.
Exploring how deep learning and a pre-trained geolocation model can be used to automate and improve performance in the GeoGuessr geographic discovery game.
Explains the physics and optics behind why smartphone portrait mode uses artificial blur instead of true optical depth of field.
A curated list of public dataset repositories for machine learning and deep learning projects, including sources for computer vision, NLP, and more.
A curated list of public dataset repositories for machine learning and deep learning projects, including computer vision and NLP datasets.
Explores video segmentation techniques like rotoscoping and green screens used in Hollywood VFX, comparing them to modern AI models like Deeplab v3+.
A tutorial on building an OCR application using Angular for the frontend and Azure Computer Vision API for text extraction from images.
A curated list of top data annotation companies worldwide, grouped by annotation type, focusing on services for computer vision, NLP, and audio data.
A technical tutorial explaining the fundamentals of Convolutional Neural Networks (CNNs) by manually calculating layers from the classic LeNet-5 architecture.
Explores the human effort behind AI training data, covering challenges of data annotation and techniques like transfer learning to reduce labeling workload.
A curated list of open-source and free tools for data annotation across computer vision, NLP, audio, and other domains, including image and video labeling.
Explores efficient state representations for robots to accelerate Reinforcement Learning training, comparing pixel-based and model-based approaches.
Using Azure Cognitive Services and Logic Apps to automatically tag and enrich images stored in SharePoint with metadata.
Introduces PlaNet, a model-based AI agent that learns environment dynamics from pixels and plans actions in latent space for efficient control tasks.
Explores fast, one-stage object detection models like YOLO, SSD, and RetinaNet, comparing them to slower two-stage R-CNN models.
Building a Mortal Kombat controller using TensorFlow.js, CNNs, and transfer learning for posture classification from a webcam feed.
A team wins a tech hackathon by creating an AR app that uses AI and computer vision to recommend web content based on what a phone camera sees.
Explores the R-CNN family of models for object detection, covering R-CNN, Fast R-CNN, Faster R-CNN, and Mask R-CNN with technical details.
Explores classic CNN architectures for image classification, including AlexNet, VGG, and ResNet, as foundational models for object detection.
A retrospective on the transformative impact of deep learning over the past five years, covering its rise, key applications, and future potential.
