1.  Introduction to Generative AI.
2. AI vs ML vs DL vs NLP vs Generative AI.
3. Generative AI principles.
4. What is the role of ML in Gen-AI.
5. Different ML techniques (Supervised, Unsupervised, Semi-supervised & Reinforcement Learning).
6. Applications in various domains.
7. Ethical considerations.

1. NLP essentials.
2. Basic NLP tasks.
3. Different text classification approaches.
4. Frequency-based – Bag of words, TF-IDF, N-gram.
5. Distribution Models – CBOW, Skipgram(Traditional approaches)and
   word2vec, Glove.
6. Ensemble Methods (Random Forest, Gradient Boosting, AdaBoost) &
   Traditional Machine Learning Models – Naïve Bayes, Support Vector
   Machine (SVM), Decision Trees, Logistic Regression.
7. Deep learning techniques – CNNs, RNNs, LSTMs, GRU and
   Transformers.

1. Autoencoders.
2. VAE’s and applications.
3. GANs and it’s applications.
4. Different types of GANs and applications.

1.  Different types of Language models
2.  Applications of Language models
3. Transformers and its architecture
4.  BERT, RoBERTa, GPT variations
5. Applications of transformer models

1.  What is Prompt Engineering
2. What are the different principles of Prompt Engineering
3. Types of Different Prompt Engineering Techniques
4. How to Craft effective prompts to the LLMs
5.  Priming Prompt
6. Prompt Decomposition

1. Generative AI lifecycle
2. What is RLHF
3.  LLM pre-training and scaling
4. Different Fine-Tuning techniques

1.  What are word embeddings
2.  What is the use of word embeddings, where we can use it?
3.  Word Embeddings – Word2Vec, GloVe and FastText
4. Contextual Embeddings – ELMo , BERT and GPT
5. Sentence Embeddings – Doc2Vec, Infersent, Universal Sentence
   Encoder
6. Subword Embeddings – BPE(Byte Pair Encoding), Sentence Piece
7.  Usecase of Embeddings.

1.  What is Chunking
2. What is the use of chunking the document
3. What are the traditional effective chunking techniques
4. What are the problems and limitations with traditional chunking
   techniques?
5. How to overcome the limitations of Traditional chunking
6. Advanced Chunking Techniques:
   1. Character Splitting
   2. Recursive Character Splitting
   3. Document based Chunking
   4. Semantic Chunking
   5. Agentic Chunking

1.  What is RAG
2. What are the main components of RAG
3. High level architecture of RAG
4. How to Build RAG using external data sources
5. Advanced RAG

1. What is Langchain
2. What are the core concepts of Langchain
3. Components of Langchain
4. How to use Langchain agents

● LlamaIndex
● What are Vector Databases
● Why do we prefer Vector Databases over Traditional Databases
● Different Types of Vector Databases: OpenSource and Close Source
● OpenSource: Chroma DB, Weaviate,Faiss,Qdrant
● Close-Source Vector Databases:Pinecone,ArangoDB,Cloud-Based
Solutions

1. Supervised Finetuning
2. Repurposing-Feature Extraction
3. Advanced techniques in Supervised Finetuning -PEFT -LoRA, QLoRA

1. Text based LLMs:
   Automatic Evaluation: BULE Score, ROUGE Score, METEOR, BERT
   Score.
   Human Evaluation: Coherence, Factuality, Originality, Engagement
2.  Image based LLMs:
   Automatic Evaluation: Pixel-level metrics, FID (Frechet Inception
   Distance), IS (Inception Score), Perceptual Quality Metrics,
   Diversity Metrics.
   Human Evaluation: Photorealism, Style, Creativity, Cohesiveness
3.  Audio generation LLMs:
   Automatic Evaluation: FAD (Frechet Audio Distance), IS (Inception
   Score), Perceptual Quality Metrics – PAQM, PAQM – SNR (Signal-to-Noise Ratio), PAQM – PESQ (Perceptual Evaluation of Speech
   Quality)
   Human Evaluation:Perceptual Quality – PQ, PQ- Naturalness, PQFidelity, PQ- Musicality, Task Specific Evaluation.
4. Video Generation LLMs:
   Automatic Evaluation: FVD (Frechet Video Distance), Inception
   Score(IS), Perceptual Quality Metrics, Motion Based Metrics –
   Optical Flow Error, Content-Specific Metrics.
   Human Evaluation: Visual Quality, Temporal Coherence, Content
   Fidelit.

1. Model Deployment and Management
2.  Scalability and Performance Optimization
3. Security and Privacy
4. Monitoring and Logging
5. Cost Optimization
6. Model Interpretability and Explainability.

1. Amazon Bedrock, Azure OpenAI

1. Chatgpt, Gemini, google Notebook LM, Copilot, Grok, mid journey, ideogram, Jasper, Copy.ai, Notion AI, DALL·E, Midjourney, Stable Diffusion,