What you'll learn

Text preprocessing
tokenization
lemmatization
bag of words
TF-IDF
n-gram
Word2Vec
continuous bag of words
skip gram
glove
Neuron
word embeddings
Convolutional Neural Network
Recurrent neural network
LSTM
Variational Autoencoders (VAEs)
Introduction to GAN
Introduction to attention
Introduction to Transformer architecture
Introduction to self-attention
Introduction to Multi-Head Self Attention
Introduction to Positional encoding
Introduction to Encoder-decoder structure
Introduction to BERT
Introduction to GPT
What is LLM
Introduction to BLEU
Introduction to FID
Introduction to extrinsic evaluation metrics?
Introduction to fine tuning
Introduction to multimodal foundation model
Introduction foundation models
Introduction to full fine-tuning
Introduction to parameter-efficient fine-tuning (PEFT)
Introduction to adapter based fine tuning
Introduction to emergent abilities
Introduction to unsupervised learning
Introduction to masked language modeling (MLM)
Introduction to self supervised learning
Introduction to contrastive learning
Introduction to reinforcement learning from human feedback (RLHF)?
Introduction to knowledge distillation

Course content

5 sections • 96 lectures • 9h 10m total length

Introduction1:17
How to make the most out of this course1:52
What is Generative AI and why do we need to learn2:21
What is Text preprocessing4:13
What is tokenization2:23
What is stemming3:30
What is lemmatization3:20
Simple tokenization, lemmatization and stemming implementation11:01
Explanation for Simple tokenization, lemmatization and stemming implementation6:09
Introduction to bag of words3:05
Introduction to TF-IDF3:25
Introduction to n-gram3:25
Bag of words, TF-IDF implementation23:23
n-gram implementation14:46
Explanation of bag of words Implementation4:25
Explanation of n-gram implementation4:15
Introduction to Word2Vec3:29
Introduction to continuous bag of words2:35
Introduction to skip gram3:35
Introduction to glove4:15
CBOW implementation Part 111:35
CBOW implementation Part 27:41
CBOW implementation Part 34:45
CBOW implementation Part 48:06
CBOW implementation Part 55:51
CBOW implementation Final Part5:29
Explanation of CBOW implementation8:20
skip gram implementation14:37
Explanation of skipgram implementation7:19
glove implementation Part 17:07
glove implementation Final Part11:44
Explanation of glove implementation5:25

What is a neuron?2:12
How do neural networks learn?3:07
How are word embeddings related to neural networks?2:39
Reconstructing Context with Sequence Models3:30
Introduction to Convolutional Neural Network3:40
Introduction to Recurrent neural network3:44
What is LSTM4:14
Why aren’t sequence models enough for complex language4:05
Introduction to Variational Autoencoders (VAEs)3:37
Introduction to GAN3:20
Introduction to attention3:40
Introduction to Transformer architecture3:50
Introduction to self-attention4:24
Implementation of self-attention12:55
Explanation of self-attention implementation6:37
Introduction to Multi-Head Self Attention4:32
Multi-Head Self Attention Implementation16:44
Explanation multi-head self attention implementation9:33
Introduction to Positional encoding3:20
Introduction to Encoder-decoder structure3:54
Introduction to BERT3:17
How does BERT work4:18
How does BERT learn3:42

Introduction to GPT?1:59
How does GPT work3:29
IMDB implementation with GPT 2 Part 116:00
IMDB implementation with GPT 2 Part 211:30
IMDB implementation with GPT 2 Part 39:40
IMDB implementation with GPT 2 Part 49:10
IMDB implementation with GPT 2 Final Part1:30
Why is GPT a decoder-only design?3:05
How GPT was trained3:20
What is LLM2:41
Why do we need to evaluate LLM?3:05
Introduction to perplexity?3:33
Introduction to BLEU3:10
Introduction to FID3:45
Introduction to extrinsic evaluation metrics?2:59
Additional Considerations in LLM Evaluation4:50
What are the challenges in evaluating LLMs4:50

Introduction foundation models2:49
Simple example implementation of foundation model15:10
Explanation for simple example implementation of foundation model9:10
Introduction to multimodal foundation model4:32
What does scale means in the context of foundation model3:55
How do models learn4:50
How does pretraining define both training and inference4:54
What does the pretraining workflow look like?5:30
Introduction to fine tuning3:24
Introduction to full fine-tuning2:45
Introduction to parameter-efficient fine-tuning (PEFT)5:07
Introduction to adapter based fine tuning4:34
What is the role of loss functions and optimization during the pretraining stage5:10
Introduction to emergent abilities3:24
Introduction to unsupervised learning4:50
Introduction to self supervised learning4:40
Introduction to masked language modeling (MLM)3:55
Masked Language Modeling (MLM) implementation with python9:35
Introduction to contrastive learning4:34
Introduction to reinforcement learning from human feedback (RLHF)?5:39
Simple RLHF Implementation22:03
Explanation of Simple RLHF implementation7:43
Introduction to knowledge distillation3:02

Requirements

Basic and advanced knowledge is required
No need to know about generative AI

Description

Core Concepts of Generative AI is an introductory–to–intermediate course designed to equip learners with a strong foundational understanding of generative artificial intelligence—its theories, methods, tools, and real-world applications. This course demystifies how modern AI systems create text, images, audio, and other content, while helping students develop the technical intuition needed to work confidently with generative models.

Learners will explore the evolution of generative AI, from early probabilistic models to today’s large language models (LLMs) such as GPT, Claude, Llama, and diffusion-based image generators like Stable Diffusion and Midjourney. Through hands-on exercises, students will practice prompt engineering, fine-tuning, evaluation methods, and responsible AI principles.

By the end of the course, students will understand how generative AI works, how to use it effectively, and how to apply it to real-world tasks across industries such as education, marketing, software development, and creative content production.

Learning Outcomes

Upon completing this course, learners will be able to:

Explain the fundamental concepts behind generative AI and machine learning.
Understand the architecture and training principles of large language models and diffusion models.
Understand generative AI tools.
Evaluate generative AI outputs for accuracy, bias, and safety.
Understand model fine-tuning, and embeddings.
Apply generative AI to solve practical problems through mini-projects.

Topics Covered

Introduction to Artificial Intelligence & Machine Learning
Large Language Models (GPT, Llama, Claude, Gemini)
Transformers & Attention Mechanisms
Diffusion Models for Image Generation
Fine-tuning and Masked Language Models Concepts
Introduction to BLEU
Introduction to FID
Retrieval-Augmented Generation (RAG)
Real-world Applications Across Industries

Who Should Take This Course?

This course is ideal for:

Students new to AI
Software developers and IT professionals
Digital content creators
Business professionals exploring AI integration
Anyone interested in understanding or applying generative AI

No advanced mathematics experience is required—just a willingness to explore and experiment.

Who this course is for:

Anyone who wants to improve python skills
Anyone who wants to get into generative AI fields
Anyone who wants to improve AI skills
Anyone who wants to become expert in generative AI fields

What you'll learn

Explore related topics

Course content

Introduction32 lectures • 3hr 25min

Introduction to Generative AI23 lectures • 1hr 55min

Introduction to GPT and LLM17 lectures • 1hr 29min

fundamental concept of foundation model23 lectures • 2hr 21min

Thank you1 lecture • 1min

Requirements

Description

Who this course is for: