NVIDIA-Certified Associate – Generative AI LLMs (NCA-GENL)

Course Curriculum

Chapter 1: Introduction

Lecture 1: Welcome to the Course

Lecture 2: Get Slide Resources – Source code

Lecture 3: What makes this course Unique

Chapter 2: Machine Learning Fundamentals

Lecture 1: Introduction to Machine Learning Fundamentals

Lecture 2: About Instructor

Lecture 3: Introduction to Machine Learning

Lecture 4: Types of Machine Learning

Lecture 5: Linear Regression & Evaluation Metrics for Regression

Lecture 6: Regularization and Assumptions of Linear Regression

Lecture 7: Logistic Regression

Lecture 8: Gradient Descent

Lecture 9: Logistic Regression Implementation and EDA

Lecture 10: Evaluation Metrics for Classification

Lecture 11: Decision Tree Algorithms

Lecture 12: Loss Functions of Decision Trees

Lecture 13: Decision Tree Algorithm Implementation

Lecture 14: Overfit Vs Underfit – Kfold Cross validation

Lecture 15: Hyperparameter Optimization Techniques

Lecture 16: KNN Algorithm

Lecture 17: SVM Algorithm

Lecture 18: Ensemble Learning – Voting Classifier

Lecture 19: Ensemble Learning – Bagging Classifier & Random Forest

Lecture 20: Ensemble Learning – Boosting Adabost and Gradient Boost

Lecture 21: Emsemble Learning XGBoost

Lecture 22: Clustering – Kmeans

Lecture 23: Clustering – Hierarchial Clustering

Lecture 24: Clustering – DBScan

Lecture 25: Time Series Analysis

Lecture 26: ARIMA Hands On

Chapter 3: Fundamentals of Deep Learning

Lecture 1: Deep Learning Fundaments – Introduction

Lecture 2: Introduction to Deep Learning

Lecture 3: Introduction to Tensorflow & Create first Neural Network

Lecture 4: Intuition of Deep Learning Training

Lecture 5: Activation Function

Lecture 6: Architecture of Neural Networks

Lecture 7: Deep Learning Model Training. – Epochs – Batch Size

Lecture 8: Hyperparameter Tuning in Deep Learning

Lecture 9: Vanshing & Exploding Gradients – Initializations, Regularizations

Lecture 10: Introduction to Convolutional Neural Networks

Lecture 11: Implementation of CNN on CatDog Dataset

Lecture 12: Transfer Learning for Computer Vision

Lecture 13: Feed Forward Neural Network Challenges

Lecture 14: RNN & Types of Architecture

Lecture 15: LSTM Architecture

Lecture 16: Attention Mechanism

Lecture 17: Transfer Learning for Natural Language Data

Chapter 4: Essentials of NLP

Lecture 1: Introduction to NLP Section

Lecture 2: Introduction to NLP and NLP Tasks

Lecture 3: Understanding NLP Pipeline

Lecture 4: Text Preprocessing Techniques – Tokenization

Lecture 5: Text Preprocessing – Pos Tagging, Stop words, Stemming & Lemmatization

Lecture 6: Feature Extraction – NLP

Lecture 7: One Hot Encoding Technique

Lecture 8: Bag of Words & Count Vectorizer

Lecture 9: TF IDF Score

Lecture 10: Word Embeddings

Lecture 11: CBoW and Skip gram – word embeddings

Chapter 5: Large Language Models

Lecture 1: Introduction to Large Language Models

Lecture 2: How Large Language Models (LLMs) are trained

Lecture 3: Capabilities of LLMs

Lecture 4: Challenges of LLMs

Lecture 5: Introduction to Transformers – Attention is all you need

Lecture 6: Positional Encodings

Lecture 7: Positional Encodings – Deep Dive

Lecture 8: Self Attention & Multi Head Attention

Lecture 9: Self Attention & Multi Head Attention – Deep Dive

Lecture 10: Understanding Masked Multi Head Attention

Lecture 11: Masked Multi Head Attention – Deep Dive

Lecture 12: Encoder Decoder Architecture

Lecture 13: Customization of LLMs – Prompt Engineering

Lecture 14: Customization of LLMs – Prompt Learning – Prompt Tuning & p-tuning

Lecture 15: Difference between Prompt Tuning and p-tuning

Lecture 16: PEFT – Parameter Efficient Fine Tuning

Lecture 17: Training data for LLMs

Lecture 18: Pillars of LLM Training Data: Quality, Diversity, and Ethics

Lecture 19: Data Cleaning for LLMs

Lecture 20: Biases in Large Language Models

Lecture 21: Loss Functions for LLMs

Chapter 6: Prompt Engineering for the NCA-GENL Exam

Lecture 1: What is Prompt Engineering ?

Lecture 2: Advanced Prompt Engineering

Lecture 3: Techniques for Effective Prompts

Lecture 4: Ethical Considerations in Prompt Design for Large Language Models

Lecture 5: NVIDIA's Tools and Frameworks for Prompt Engineering

Lecture 6: NVIDIA Ecosystem tools for LLM Model Training

Chapter 7: Data Analysis and Visualization

Lecture 1: Data Visualization & Analysis of LLMs

Lecture 2: EDA for LLMs

Chapter 8: Experimentation

Lecture 1: Experiment Design Principles for LLMs

Lecture 2: Techniques for Large Language Models Experimentation

Lecture 3: Data Management and Version Control for LLM experimentation

Lecture 4: NVIDIA Ecosystem tools for LLM Experimentation, Data Management and Version Cont

Chapter 9: LLM integration & Deployment