1. Basics of NLP.
2. Key NLP tasks.
3. Various methods for text classification.
4. Frequency-based methods: Bag of Words, TF-IDF, N-gram.
5. Distribution models: CBOW, Skipgram (traditional methods), word2vec, and GloVe.
6. Ensemble methods: Random Forest, Gradient Boosting, AdaBoost, along with traditional machine learning models like Naïve Bayes, Support Vector Machine (SVM), Decision Trees, and Logistic Regression.
7. Deep learning methods: CNNs, RNNs, LSTMs, GRU, and Transformers.

1. Autoencoders.
2. Variational Autoencoders (VAEs) and their uses.
3. Generative Adversarial Networks (GANs) and their uses.
4. Various types of GANs and their applications.

1. Types of Language Models
2. Uses of Language Models
3. Understanding Transformers and Their Structure
4. BERT, RoBERTa, and Variations of GPT
5. Uses 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. How are word embeddings used, and where can they be applied?
3. Types of Word Embeddings: Word2Vec, GloVe, and FastText
4. Contextual Embeddings: ELMo, BERT, and GPT
5. Sentence Embeddings: Doc2Vec, Infersent, and Universal Sentence Encoder
6. Subword Embeddings: BPE (Byte Pair Encoding) and Sentence Piece
7. Applications of Embeddings.

1. What is RAG?
2. What are the key parts of RAG?
3. Overview of RAG architecture.
4. How to create RAG with outside data sources.
5. Advanced RAG techniques.

1. Introduction to Langchain
2. Key ideas of Langchain
3. Parts of Langchain
4. Using Langchain agents.

1. LlamaIndex
2.  Understanding Vector Databases
3.  Advantages of Vector Databases Compared to Traditional Databases
4.  Types of Vector Databases: Open Source and Closed Source
5.  Open Source Examples: Chroma DB, Weaviate, Faiss, Qdrant
6.  Closed 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. mage-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, PQ – Fidelity, 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 Fidelity.

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, Copilot