- Git and GitHub for Beginners - Crash Course
- MLops and Github Actios Tutorial
- Awesome MLOps Detailed Resources
- Why and How to create requirements.txt
- Need of Data Structures and Algorithms for Deep Learning and Machine Learning
- Python for Data Structures, Algorithms, and Interviews! Udemy Course
- Algorithms and Data Structures in Python (INTERVIEW Q&A)
- Tensorboard detailed tutorial
- Tensorboard by Siraj
- How to visualize convolutional features in 40 lines of code
- Guide to real-time visualisation of massive 3D point clouds in Python
- Ploty 3D visualization tool for python
- Gradient-weighted Class Activation Mapping - Grad-CAM
- WeightsBiases Channel
- Guide to implement playlist
- Advanced Deep Learning Playlists
- Explore/Exploit: Hyperparameter Tuning with W&B Sweeps by Stacey Svetlichnaya
- Pipeline Versioning with W&B Artifacts
CVonline: Image Databases COmputer Vision Dataset Fashion Image Object Detection Dataset and Project(due project)
- Deep Learning tools and Extensive Guide, Study
- Deep Learning Architectures Paper Explained
- Ian Goodfellow, Yoshua Bengio, Aaron Courville - Deep Learning (2017, MIT).pdf
- Deep Learning Computer Vision IIT Madras NPTEL Playlist
- Graph CNN Resources
- Machine learning with Graphs Highly recommened for GNN/GCN
- Use GCN lectues of that DL series for implementation
- What's the hardware spec for Google Colaboratory?
- Random Forest
- CS 329S: Machine Learning Systems Design
- Deep learning doesn’t need to be a black box
- Comprehensive Introduction to Autoencoders
- An Overview of Deep Learning Based Clustering Techniques
- The 5 Clustering Algorithms Data Scientists Need to Know
- Python Data Science Cheatsheet
- ML models Compression and Quantization
- Pandas Cheatsheet
- Pytorch Lighting Masterclass
- [Hyper-parameter optimization algorithms: a short review](https://medium.com/criteo-engineering/hyper-parameter-optimization-algorithms-2fe447525903#:~:text=BOHB%20(Bayesian%20Optimization%20and%20HyperBand,Hyperband%20algorithm%20and%20Bayesian%20optimization.&text=It%20uses%20Hyperband%20to%20determine,estimator%20with%20no%20tree%20structure)
- Comparing Modern Scalable Hyperparameter Tuning Methods
- Practical Recommendations for Gradient-Based Training of Deep Architectures
- Best SVM Lectures
- Insight of Kernelization
- SVM followup of Codeemporium
- Boosting - EXPLAINED!
- Ensemble Learning | Ensemble Learning In Machine Learning | Machine Learning Tutorial | Simplilearn
- State-of-the-art Learning Rate Schedules
- Competition Winning Learning Rates
- CS7015 DEEP LEARNING BEST DL FULL NPTEL COurse
- How do GPUs speed up Neural Network training?
- Why use GPU with Neural Networks?
- A Short Introduction to Entropy, Cross-Entropy and KL-Divergence
- Why do we need Cross Entropy Loss? (Visualized)
- Loss Functions - EXPLAINED!
- Why do we need Cross Entropy Loss? (Visualized)
- Subgradient Descent
- Maximum Likelihood Estimation-II, Square Error Loss Derivation
- Maximum-likelihood understanding
- Maximum Likelihood For the Normal Distribution, step-by-step!
- CS229: Machine Learning - The Summer Edition!
- Find and Remove duplicates using 51
- Data-Driven Control with Machine Learning
- AliGhodsi Lec 12, Metric Learning
- 8.5 David Thompson (Part 5): Metric Learning
- The Why and the How of Deep Metric Learning.
- OpenCV cpp course
- OpenCV cpp video tutorial
- OpenCV Python for Beginners - Full Course in 10 Hours - Learn Computer Vision with OpenCV
- Deep Learning using C++
- CUDA Programming masterclass udemy
- Computer Vision by using C++ and OpenCV with GPU support
- CppCon 2017: Peter Goldsborough “A Tour of Deep Learning With C++”
- Keras In Tensorflow C++
- Deep Learning with C++ - Peter Goldsborough - Meeting C++ 2017 implement GAN
- Deep Learning on Image Denoising: An Overview
- MIXTURE OF PRE-PROCESSING EXPERTS MODEL FOR NOISE ROBUST DEEP LEARNING ON RESOURCE CONSTRAINED PLATFORMS, for object detection in noisy images
- Noise in image processing
- CNN Cheatsheet
- 7 Types of Classification Algorithms
- 5 Papers on CNNs Every Data Scientist Should Read
- Siraj Raval CNN evolution guide
- Must Study About The CNN Visualization
- Methodology to tackle Adverserial Attacks on images and analytics
- EfficientDet: Scalable and Efficient Object Detection
- Capsule Networks: The New Deep Learning Network
- Review: Xception — With Depthwise Separable Convolution
- Xception Pytorch
- Implementing Grad-CAM in PyTorch
- CURL: Neural Curve Layers for Global Image Enhancement (ICPR 2020)
- Interpretability in Deep Learning CNN
- keras-gradcam
- Why do most CNN models not apply the cross-validation technique?
- Classification models Zoo - Keras (and TensorFlow Keras) all standard model implementations
- EfficientNet Keras Implementation
- Everything you need to know about MobileNetV3 and its
- Residual Attention for image classification
- Residual Attention Network Github Implementation
- A Basic Introduction to Depthwise Separable Convolutions
- Understanding Semantic Segmentation with UNET
- Keras Applictions of Available Models for Transfer Learning
- Tensorflow Applications of available models
- Visualizing and Understanding Convolutional Networks - ZFNet
- Receptive Fields - Intro to Neural Computation from perspective of cognitive science
- Advanced Machine Learning Day 3: Neural Architecture Search
- 2016 DenseNet paper summary
- 2016 DenseNet paper summary
- ConvNets Scaled Efficiently Efficientnet
- Attention and Transformers Detailed Blogs
- DropBlock - A BETTER DROPOUT for Neural Networks
- Neural Network Playground
- Spatial Dropout
- 2-Dimensional Nyquist Sampling Theory
- [ICML19 Talk] Making Convolutional Networks Shift-Invariant Again (06/2019)
- 05 Imperial's Deep learning course: Equivariance and Invariance
- Semi-supervised Image Classification With Unlabeled Data
CNN Intuitions refereneces
- What do filters of Convolution Neural Network learn?
- Understanding the Role of Individual Units in a Deep Neural Network
- Receptive fields and Effective receptive fields
- Receptive Field Intuition
- Depthwise Separable Convolution - A FASTER CONVOLUTION!
- Introduction to Different types of Convolutions
- Dilated Convolution
- Transposed Convolution
- Upsampling and Transposed Convolution
- Interpretable Convolutional Neural Network
- Review: Tompson CVPR’15 — Spatial Dropout (Human Pose Estimation)
- Evolution of Object Detection Guide
- Evolution of Object Detection Guide Playlist
- CS231n Winter 2016: Lecture 8: Localization and Detection
- YOLOV4 advanced paper study
- YOLOv4 explanation must watch, training strategies
- YOLOv4 series for implementation
- Mask Region based Convolution Neural Networks - EXPLAINED!
- Pre deep learning object detector, object tracking, CV3DST - Two-stage object detectors(Region Families) best playlist on object detection, tracking, semantic segmentation
- Selective Search for Object Recognition
- YOLOv4 Best Blog post to explain YOLOv4
- YOLOV4 Reading Notes
- YOLOv5 New Version - Improvements And Evaluation
- EVOLUTION OF YOLO ALGORITHM AND YOLOV5: THE STATE-OF-THE-ART OBJECT DETECTION ALGORITHM
- Best blog on Region Proposals - What do we learn from region based object detectors (Faster R-CNN, R-FCN, FPN)?
- Image segmentation with Mask R-CNN
- PANet: Path Aggregation Network In YOLOv4
- EfficientDet: Scalable and Efficient Object Detection
- MLT init Session #4 – SSD: Single Shot MultiBox Detector
- Neural Networks Intuitions: 8. Translation Invariance in Object Detectors
- ADD TO QUEUE TensorFlow model optimization: Quantization and pruning (TF World '19)
- ADD TO QUEUE Inside TensorFlow: TF Model Optimization Toolkit (Quantization and Pruning)
- Deep Dive on PyTorch Quantization - Chris Gottbrath
- Pruning Deep Learning Models for Success in Production
- Advanced Machine Learning with Neural Networks 2021 - Class 8 - Quantization and pruning
- Time Series Anomaly Detection Algorithms
- A Guide For Time Series Prediction Using Recurrent Neural Networks (LSTMs)
- DeepAnT: A Deep Learning Approach for Unsupervised Anomaly Detection in Time Series
- A Long Short-Term Memory Ensemble Approach for Improving the Outcome Prediction in Intensive Care Unit
- Time Series Anomaly Detection Algorithms
- The Promise of Recurrent Neural Networks for Time Series Forecasting
- Deep Learning Time Series Forecasting
- BERT Research Series
- Live Session- Encoder Decoder,Attention Models, Transformers, Bert Part 1
- Live- Attention Models, Transformers In depth Intuition Deep Learning- Part 2
- Live -Transformers Indepth Architecture Understanding- Attention Is All You Need
- Time series GAN
- Deep generative models to counter class imbalance: a guided model selection strategy
- Naturalistic Image Synthesis Using Variational Auto-Encoder
- Photorealistic Facial Expression Synthesis by the Conditional Difference Adversarial Autoencoder (Assignment paper)[This paper gives a review of all types of GAN Facial_Expression_Transfer_using_Generative_Advers.pdf]
- GCP AI model deployment
- How to Deploy a Machine Learning Model to Google Cloud for 20%
- Coursera MLops Fundamentals course
- Continuous Deployment from git using Cloud Build
- Mobile Deep Learning with TFlite, ML kit and Flutter, Use this for TFlite model conversion
- MIT Deep Learning 2020 projects
- Generation of music pieces using machine learning: long short-term memory neural networks approach
- Vision in Art and Neuroscience Fall 2021
- Simple, Powerful, and Fast— RegNet Architecture from Facebook AI
- Recurrent Space-time Graph Neural Networks
- Factorization Machines for Item Recommendation with Implicit Feedback Data
- Advanced Deep Learning syllabus Deploying TinyML
- implicit learning
- Convolutional occupancy networks
- New deep learning models require fewer neurons research from MIT for autonomous car
- An Embodied View of Octopus Neurobiology
- SEER: The start of a more powerful, flexible, and accessible era for computer vision [Yan Lecun Paper on Self-supervised Learning of Facebook AI team]
- Graph Neural Network paper
- Multichannel autocalibration for the Atmospheric Imaging Assembly using machine learning
- Advancing the state of the art in computer vision with self-supervised Transformers and 10x more efficient training
- Yann LeCun - Self-Supervised Learning: The Dark Matter of Intelligence (FAIR Blog Post Explained)
- AI-Crowd Crowdsourcing AI to Solve Real-World Problems
- 12 Data Science & AI Competitions to Advance Your Skills in 2021