AI and Deep Learning Explained - CNNs, Transformers, GANs, YOLO, GNNs and More

Code With Aarohi via YouTube

Start learning Write review

Explore a comprehensive deep learning tutorial series covering 115 step-by-step lessons that progress from fundamental neural network concepts to cutting-edge AI technologies. Begin with foundational topics including perceptrons, single-layer and multi-layer networks, activation functions, and optimizers before advancing to sophisticated architectures like Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), and Transformers. Master computer vision through detailed implementations of ResNet, VGGNet, EfficientNet, Inception, and DenseNet architectures, then dive into object detection with comprehensive coverage of YOLO versions 3 through 11, Faster R-CNN, SSD, and Mask R-CNN for instance segmentation. Discover generative models including GANs and their variants (DCGAN, StyleGAN, CycleGAN), explore natural language processing with RNNs and Transformers, and learn practical implementations using TensorFlow, Keras, and PyTorch frameworks. Gain hands-on experience with real-world projects including video classification using CNN-RNN architectures, custom dataset training, object tracking with DeepSORT, and web applications using Flask. Advanced topics include Graph Neural Networks, Vision Transformers, the Segment Anything Model (SAM) from Meta AI, 3D object detection with LiDAR data, and introductions to Artificial General Intelligence (AGI) and Google's PaLM language model, providing a complete roadmap for mastering artificial intelligence and deep learning from beginner to advanced levels.

Syllabus

L-1 Introduction to Deep Learning
L-2 Activation Functions in Deep Learning
L-3 TensorFlow Basics | Computational Graphs, Constants, Variables & Placeholders
L-4 Perceptron | Single Layer Neuron
L-5 Perceptron Implementation | Single Layer Perceptron
L-6 Optimizers & Learning Rate in Deep Learning
L-7 Implementation of Perceptron with Optimizer
L-8 What is Bias | Why We Use Bias in Neural Networks
L-9 Binary Classification Using Perceptron | Single Layer Neuron
L-10 Image Classification using Perceptron | Singla Layer Neuron
L-11 Image Classification Using Multi-Layer Perceptron (MLP) with Keras
L-12 Computer Vision Vs Image Processing
L-13 Vanishing Gradients | Deep Learning Problem & Solution
Convolutional Neural Network Explained | CNN | Deep Learning Tutorial
Master Convolutional Neural Networks | Deep Learning Image Classification Tutorial
Padding in CNN Explained | Zero, Same & Valid Padding with Stride Tutorial
LeNet Explained | Layer-by-Layer CNN Architecture Guide
AlexNet Explained Step by Step | Deep Learning & CNN Tutorial
VGG16 Tutorial | Build & Train Your Own Convolutional Neural Network
ResNet Explained Step by Step( Residual Networks)
Explained Identity Block and Convolution Block in ResNet | Residual Networks
ResNet Using Keras | Residual Network | Convolutional Neural Network | Deep Learning & CNN Tutorial
EfficientNet Explained: Rethinking Model Scaling for Convolutional Neural Networks
EfficientNet Implementation | EfficientNet B0 - B7 Implementation
EfficientNet on Custom Dataset | Image Classification Using EfficientNet
Training Neural Networks on GPU vs CPU | Performance Test
Inception Network | Inception Module | InceptionV1
InceptionV3 | Inception Network
Inception V3 Practical Implementation | InceptionV3
DenseNet | Densely Connected Convolutional Networks
DenseNet-121 Implementation on Custom Dataset | DenseNet
YOLO - Object Detection Using Python
Object Detection Using Yolo | Yolo V 3 network from scratch using Python
Object Detection Using YOLO v4 on Custom Dataset | Practical Implementation
Traffic Sign Detection Using Yolo V4 | Yolov4 on Custom Dataset
Object Detection Using YOLOv4-tiny | Part 1
Install Darknet framework | Object Detection using yolov4
TFLite Object Detection Android App Tutorial | Object Detection Using Yolov4 tiny
Yolo v5 on Custom Dataset | Train and Test Yolov5 on Custom Dataset
Leaf Disease Detection using yolov5 | Object Detection
Image Classification Using YOLOv5
Object Tracking Using DeepSORT and YOLOv5 | Multi Object Tracking
TFLite Object Detection Android App Tutorial Using YOLOv5 | Yolov5 to tflite conversion
YOLOR on a Custom Dataset | Object detection using YOLOR
YOLOv6 on Custom dataset | Object Detection
YOLOv6 on Custom Dataset | Object Detection
YOLOv7 | Object Detection | instance segmentation | keypoints detection
YOLOv7 | Object Detection on Custom Dataset
YOLOv7 | Instance Segmentation on Custom Dataset
Official YOLOv7 | Object Detection
YOLOv8 | Object Detection on a Custom Dataset using YOLOv8
YOLOv8 | Image Segmentation On Custom Dataset using YOLOv8
YOLOv8 Object Detection with Flask | Object Detection Web Application
Object Tracking using YOLOv8 on Custom Dataset
Object Tracking using YOLOv8 on Custom Dataset - Google Colab
Mask R-CNN Practical Implementation
Plant leaf disease detection using Mask R-CNN | Image Segmentation
Instance Segmentation Using Mask R-CNN on Custom Dataset
Instance Segmentation Web Application Using Mask R-CNN and FLask
Segment Anything Model (SAM): a new AI model from Meta AI
Segment Anything Model (SAM): Build Custom Image Segmentation Model Using YOLOv8 and SAM
Auto Annotation for generating segmentation dataset using YOLOv8 & SAM
Key point Detection On Custom Dataset Using YOLOv7 | YOLOv7-Pose on Custom Dataset
Object Detection Using YOLOv7 and Flask | Object Detection Web Application
Master YOLOv8 Keypoint Detection | YOLOv8-Pose | Keypoint Detection for Beginners
YOLO-NAS Custom Object Detection | Fall Detection Using YOLO-NAS
YOLO-NAS + SAM : Image Segmentation Using YOLO-NAS and Segment Anything Model
YOLO-NAS and StrongSORT | Object detection and tracking
Single Shot Detector On Custom Dataset | SSD | Object Detection Using SSD
Single Shot Detector On Custom Dataset | Google Colab Implementation | Object Detection
Single Shot Detector On Custom Dataset | Test your Custom SSD Model
1 Object Detection Using Faster R-CNN
2 Faster R-CNN | Object Detection Using Faster R-CNN
3 Region Proposal Network | Faster R-CNN
4 Region Of Interest (RoI Pooling) | Faster R-CNN | Object Detection Using Faster R-CNN
Faster R-CNN on Custom Dataset | Custom Object Detector
Single Shot Detector | SSD | Object Detection Using SSD
L-1 Single Shot Detector Practical Implementation
L-2 Single Shot Detector | Code for SSD Model
L-3 Single Shot Detector | Model Testing
Video Classification with a CNN-RNN Architecture | Human Activity Recognition
3D Object Detection using YOLO4 | LiDAR Dataset
Open3D Tutorial | 3D Data Processing | Visualize 3D Data
L-14 Face Detection using OpenCV
L-15 Face Recognition Using LBPH Face Recognizer
L 1 PyAudio Basics
L 1 NLP Basics( Tokenization, Stemming, Lemmatization, Stopwords)
L 2 NLP Bag Of Words(Count Vectorizer)
L 2 NLP Remove Punctuation
L 3 NLP Collacations
L 4 NLP Word Embedding | Natural Language Processing | word2vec
L 5 word2vec model train and test full code
L 6 RNN Introduction
L 6 RNN on Reuters Dataset
L-7 Sentiment Analysis using RNN on Custom Dataset
L 8 Next Word Prediction using RNN
L 9 Language Translator using seq2seq Model (RNN)
Record and Play Audios Using PyAudio
What Are GANs? | Generative Adversarial Networks Explained
Generative Adversarial Networks (GAN) - implementation in Keras
DCGAN | Deep Convolutional Generative Adversarial Network
StyleGAN Explained
StyleGAN Implementation
StyleGAN2 ADA on Custom Dataset |StyleGAN2 with adaptive discriminator augmentation (ADA)
StackGAN | Text to Image Generation with Stacked Generative Adversarial Networks
CycleGAN | Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks
Transformers for beginners | What are they and how do they work
Vision Transformers explained
Image Classification Using Vision Transformer | ViTs
Vision Transformer for Image Classification Using transfer learning
Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
Image Classification Using Swin Transformer
Graph Neural Networks
Pathways Language Model | PaLM
Artificial General Intelligence | AGI