CNN
- Convolutional Neural Networks (CNNs / ConvNets)
(link)
- 1×1 Convolution In Detail
(link)
- Comprehensive look at 1X1 Convolution
(link)
- 6 Significant Computer Vision Problems Solved by ML
(link)
- A Comprehensive Guide to Convolutional Neural Networks — the ELI5 way
(link)
- How to Train Your ResNet
(link)
- Convolution arithmetic tutorial
(link)
- Transposed Convolutions explained with… MS Excel!
(link)
- Up-sampling with Transposed Convolution
(link)
- CNNs from different viewpoints
(link)
Enhancing Photos With Deep Learning
Image Segmentation / Object Detection
- Mediapipe
(link)
- ActionDetectionforSignLanguage
(link)
- UNet
(link)
- SemTorch - Architectures definitions for image segmentation
(link)
- DE:TR: End-to-End Object Detection with Transformers
(link)
- Review: YOLOv3 — You Only Look Once (Object Detection)
(link)
- R-CNN (Object Detection)
(link)
- Review of Deep Learning Algorithms for Object Detection
(link)
- Image Segmentation in 2021: Architectures, Losses, Datasets, and Frameworks
(link)
- Review of Deep Learning Algorithms for Image Semantic Segmentation
(link)
- R-CNN, Fast R-CNN, Faster R-CNN, YOLO — Object Detection Algorithms
(link)
- YOLO (v3) object detector from scratch in PyTorch
(link)
- Image Processing with Python — Unsupervised Learning for Image Segmentation
(link)
- Fastai - Video
(link)
- FastFCN git
(link)
Misc
- Document Denoising Using Deep Learning
(link)
- Few shot learning — learning to learn from a few examples
(link)
- Paper Explained- Vision Transformers
(link)
- Why gradient descent doesn’t converge with unscaled features?
(link)
- Generalization in Neural Network
(link)
- Sarcasm detection in news headlines — on cAInvas
(link)
- Contrastive Representation Learning
(link)
- CLIP git
(link)
- DALL·E: Creating Images from Text
(link)
- Image Data Labelling and Annotation — Everything you need to know
(link)
- Activation Functions — All You Need To Know!
(link)
- Loss Functions Explained
(link)
- Deep Dive into Math Behind Deep Networks
(link)
- Everything you need to know about “Activation Functions” in Deep learning models
(link)
- Weight Initialization Techniques in Neural Networks
(link)
(link)
- Understanding Variational Autoencoders (VAEs)
(link)
- Table Detection, Information Extraction and Structuring using Deep Learning
(link)
- Deconvolution and Checkerboard Artifacts
(link)
- Troubleshooting Deep Neural Networks
(link)
Optimization Methods
- Vectorizing Gradient Descent — Multivariate Linear Regression and Python implementation
(link)
- The LookAhead optimizer
(link)
- New Deep Learning Optimizer, Ranger: Synergistic combination of RAdam + LookAhead for the best of both.
(link)
- Understanding Optimizers
(link)
“Adam” and friends
(link)
- Adam — latest trends in deep learning optimization.
(link)
- Various Optimization Algorithms For Training Neural Network
(link)
- Which Optimizer should I use for my Machine Learning Project?
(link)
- Gradient Descent
(link)
- Gradient Descent Algorithm — a deep dive
(link)
- Intro Momentum, RMSProp and Adam
(link)
- An overview of gradient descent optimization algorithms
(link)
- BatchNorm 1
(link)
- BatchNorm 2
(link)
- BatchNorm 3
(link)