This course covers foundational to advanced AI concepts:

• Understanding LLMs, Inference & Training

• Embeddings, Vector Databases, Semantic Search

• Prompt Engineering, RAG (Retrieval Augmented Generation)

• AI Agents & Multimodal AI (Vision, Audio, Speech, Text)

• Open Source vs Proprietary AI Models

• Ethics, Safety, Bias & Fairness in AI

• Tools: OpenAI, Hugging Face, Ollama, LangChain, LlamaIndex

An industry-aligned, end-to-end program:

• Python (from basics to OOP, file handling, decorators)

• Numpy, Pandas, Matplotlib, Seaborn, Plotly

• Data Analysis & Data Visualization

• SQL, Git, GitHub, Streamlit, Tableau

• Statistics (Descriptive, Inferential, Probability, Distributions)

• Capstone Projects & Case Studies

Covers ML theory and practice:

• Regression (Linear, Polynomial), Classification (KNN, SVM, Logistic)

• Tree-based models (Decision Trees, Random Forest, XGBoost, CatBoost, LightGBM)

• Clustering (KMeans, DBSCAN, GMM, Hierarchical)

• Feature Engineering, Regularization, Hyperparameter Tuning

• Dimensionality Reduction (PCA, t-SNE, LDA)

• Model Evaluation (ROC, AUC, Cross-validation)

Currently focused on Python:

• Core Programming Concepts

• Data Structures: Lists, Tuples, Dictionaries, Sets

• OOPs: Classes, Inheritance, Encapsulation, Polymorphism

• Advanced Topics: Generators, Iterators, Decorators

• GUI Development (Tkinter), Flask Web Development

• Exception Handling, Serialization (Pickle, JSON)

An emerging and practical-focused track:

• Use of LLMs (OpenAI, Claude, Gemini, Mistral)

• Fine-tuning vs RAG

• AI Agents, Chatbots, Assistant APIs

• Prompt Engineering Techniques (ReAct, Function Calling)

• Building multimodal applications (Text + Vision + Audio)

• Embeddings, Semantic Search & Recommendation Systems

While not deeply detailed in the PDFs, this course typically includes:

• Frontend: HTML, CSS, JavaScript, React.js

• Backend: Node.js, Express.js

• Database: MongoDB

• API Integration, Authentication, Deployment

Aptitude training (typically aligned with placements & competitive exams) may include:

• Number systems, Time & Work, Speed & Distance

• Profit & Loss, Averages, Percentages

• Data Interpretation

Training in logical thinking and analysis:

• Puzzles, Series, Directions

• Blood Relations, Syllogisms

• Coding-Decoding, Statements & Assumptions