Author: Ranjan Kumar
Object Detection and Recognition
Important Links Face Recognition: Understanding LBPH Algorithm – Link
Computer Vision Notes
Canny Edge Detection & Sobel Edge Detection Edge Detection by Derivation, Sobel, Scharr & Prewitt Operators Laplacian of Gaussian Simplified Image Enhancement Image Blending with Pyramids Image Fusion Epipolar Geometry
Image Fusion/Blending
Important Links: Image Pyramids (Gaussian Pyramid, Laplacian Pyramid, Image Blending using Image Pyramids, OpenCV) Image Processing using OpenCV References Image Fusion Techniques: A Survey by Harpreet Kaur, Deepika Koundal & Virender Kadyan
Important Topics/Terminologies in ML/AI
L0 Norm, L1 Norm, L2 Norm & L-Infinity Norm Data vs. Model Parallelism Dictionary learning for sparse representation – Link1 Entropy: It is the measure of the disorder / uncertainty / randomness in the information being processed. Our goal normally in machine learning is normally to reduce this. Mathematical formula of Entropy (sometime also represented…
Federated Learning
Articles Secure, privacy-preserving and federated machine learning in medical imaging – Link Federated Learning – Privacy-Preserving Collaborative Machine, Learning without Centralized Training Data – Link Federated Learning in Healthcare (WiSe2020) – Link A Beginners Guide to Federated Learning by Dr. Santanu Bhattacharya The New Dawn of AI: Federated Learning – Democratized and Personalized AI, with…
Use case: Crowd Counting
Application Areas[2]: Video Surveillance Event Planning and Space Design: Crowd counting can be applied in scenarios like public rallies, sports events, etc. for finding out the density of participating people. This information can be very crucial for future event planning and space design. Extended Applications: Methods used here can also be applied to counting cells…
Interpretable AI
Interpretable Machine Learning – A Guide for Making Black Box Models Explainable – Christoph Molnar – Link Interpretable AI – Building explainable machine learning systems, Ajay Thampi – Link Papers Multi-Objective Counterfactual Explanations by Susanne Dandl, Christoph Molnar, Martin Binder, Bernd Bischl – Link Preserving Causal Constraints in Counterfactual Explanations for Machine Learning Classifiers by…
Differential Privacy
Papers/Articles Differential Privacy: The Pursuit of Protections by Default (A discussion with Miguel Guevara, Damien Desfontaines, Jim Waldo, and Terry Coatta) – November 20, 2020 Volume 18, issue 5 (ACM queue) – Link Differentially Private SQL with Bounded User Contribution by Royce J Wilson, Celia Yuxin Zhang, William Lam, Damien Desfontaines, Daniel Simmons-Marengo, and Bryant…
Dependable AI
Papers Towards Evaluating the Robustness of Neural Networks – Nicholas Carlini, David Wagner, University of California, Berkeley – Link Defense against Universal Adversarial Perturbations – Naveed Akhtar, Jian Liu, Ajmal Mian – Link Local Gradients Smoothing: Defense against localized adversarial attacks – Muzammal Naseer, Salman H. Khan – Link Sparse and Imperceivable Adversarial Attacks –…