AI/ML beginners, data scientists, developers, and students interested in deep learning and NLP

Basic Python programming experience. No prior deep learning knowledge required.

Course Outline:

Introduction to Deep Learning and Neural Networks

1. What is deep learning?
2. Neural network architecture
3. Key components: neurons, layers, activation functions
4. How machines “learn” patterns

Introduction to PyTorch

1. What is PyTorch?
2. Core PyTorch concepts:
   1. Tensors
   2. Autograd
   3. Neural network modules
3. Setting up your environment (brief walkthrough)
4. Hands-on: Tensor operations and basic computations in PyTorch

Building Neural Networks with PyTorch

1. Defining models using Module
2. Loss functions and optimizers
3. Training loops explained
4. Hands-on: Build and train a simple deep learning model

Large Language Models (LLMs) Fundamentals

1. What are LLMs?
2. Transformer architecture
3. Popular LLMs: GPT, BERT
4. Representation models vs. generative models
5. Tokens and embeddings
6. Practical challenges: dataset size, computational requirements, ethical issues

Using Pretrained Models with Hugging Face

1. Introduction to the Hugging Face ecosystem
2. Exploring transformers library
3. Loading and using a model
4. Hands-on: Text classification with a pretrained model

Fine-tuning Pretrained Models

1. Overview of fine-tuning
2. Fine-tuning a Hugging Face model on custom data (small dataset)
3. Hands-on: Fine-tuning exercise

Best Practices and Real-World Applications

1. Choosing the right model for your task
2. Monitoring training and evaluating performance
3. Real-world examples: Chatbots, document summarization, code generation

Training material provided: Yes (Digital format)