Skip to content

Latest commit

 

History

History
102 lines (78 loc) · 4.14 KB

README.md

File metadata and controls

102 lines (78 loc) · 4.14 KB

Master Deep Learning and Generative AI with PyTorch

Welcome to the repository for "Master Deep Learning and Generative AI with PyTorch". This repository serves as a structured learning path covering fundamental to advanced deep learning concepts using PyTorch.

📚 Course Overview

This course covers the following topics in-depth:

Master-Deep-Learning-and-Generative-AI-with-PyTorch/
│── README.md
│── torch/                   # Basics of PyTorch
│── linear_regression/        # Implementing Linear Regression in PyTorch
│── activation_functions/     # All Activation Functions Implementations
│── loss_and_cost_functions/  # Understanding Loss & Cost Functions
│── optimizers/               # Different Optimization Algorithms
│── projects/                 # Hands-on Deep Learning Projects
│── improve_nn_performance/   # Techniques to Improve Neural Networks
│── nlp/                      # Natural Language Processing with PyTorch
│── gen_ai_models/            # Generative AI Models (GANs, VAEs, Transformers)
│── transformers/             # Transformer Models (BERT, GPT, etc.)
│── vision_transformer/       # Vision Transformer (ViT) Implementations

🔥 Core Concepts (torch/)

  • Introduction to PyTorch tensors, operations, and autograd
  • Loading datasets with torchvision
  • Building basic neural networks

📊 Linear Regression (linear_regression/)

  • Implementing Linear Regression from scratch
  • Using PyTorch's nn.Linear for regression models
  • Loss functions and optimization for regression tasks

⚡ Activation Functions (activation_functions/)

  • Implementing and understanding activation functions:
    • Sigmoid, Tanh, ReLU, Leaky ReLU, Softmax, GELU, SiLU, etc.
  • Properties and characteristics of activation functions
  • Choosing the right activation function for your model

🎯 Loss and Cost Functions (loss_and_cost_functions/)

  • Understanding Mean Squared Error (MSE), Cross-Entropy, Huber Loss, etc.
  • Implementing loss functions in PyTorch
  • Visualizing loss functions

🚀 Optimizers (optimizers/)

  • Implementing Gradient Descent, Adam, RMSProp, AdaGrad, etc.
  • Comparison of different optimization techniques
  • Learning rate scheduling and fine-tuning

💡 Hands-on Projects (projects/)

  • Implementing end-to-end deep learning projects
  • Classification, regression, and real-world applications
  • Computer vision and NLP-based projects

⚙️ Improving Neural Network Performance (improve_nn_performance/)

  • Weight initialization techniques (Xavier, He, etc.)
  • Batch Normalization, Dropout, Regularization techniques
  • Gradient clipping, learning rate scheduling, early stopping

📝 Natural Language Processing (NLP) (nlp/)

  • Text preprocessing: Tokenization, Stemming, Lemmatization
  • Text vectorization: One-Hot Encoding, TF-IDF, Word2Vec
  • Implementing NLP models using PyTorch

🎨 Generative AI Models (gen_ai_models/)

  • Implementing Variational Autoencoders (VAEs)
  • Building Generative Adversarial Networks (GANs)
  • Diffusion models and text-to-image generation

🤖 Transformers (transformers/)

  • Attention mechanism and self-attention
  • Implementing Transformer models like BERT, GPT, T5
  • Pretrained Transformers and Fine-tuning

👀 Vision Transformer (vision_transformer/)

  • Understanding Vision Transformer (ViT)
  • Implementing Vision Transformer using PyTorch
  • Image classification using Transformer-based models

💻 Prerequisites

  • Basic programming knowledge (preferably in Python)
  • High school-level mathematics (linear algebra, calculus)
  • No prior AI/ML experience needed—this course covers everything from scratch!

📌 Who Should Join This Course?

  • AI & Deep Learning Beginners
  • Software Developers transitioning to AI/ML
  • Data Scientists looking to master PyTorch

🔗 Course Access

If you want the complete guided learning experience, enroll in the course on Udemy:
Master Deep Learning and Generative AI with PyTorch in Hindi