Artificial Intelligence Course
Best Generative AI Course from GeekBase, Exclusively designed for Working Professionals and college students. with our expert-guided training and 100% Placement Assistance.
Course overview
Artificial Intelligence with Python, APIs & Deployment (Industry-Oriented Program)
Course Description:
This comprehensive AI program equips learners with end-to-end skills—from Python programming to building, deploying, and integrating AI applications. Students will learn Machine Learning, Deep Learning, NLP, Computer Vision, and Generative AI, along with backend development using Flask, database handling, and real-world deployment.
Key Highlights:
Target Audience:
Students interested in AI/ML careers.
Developers looking to transition into AI/Machine-Learning.
Professionals aiming to upskill in AI-ML technologies..
Mentor Support:
Learners will have access to an experienced instructor who will provide support through one on one meeting, live Q&A sessions, and email to answer questions and provide guidance throughout the course period.
Curriculum
15 modulesModule 1: Python Essentials
- Introduction to Python: history, variables, data types
- Operators, Input/Output, loops
- Conditional statements, Functions, string handling, file handling
- OOP — Classes, Objects, Inheritance
- Exception handling, modules, virtual environments, JSON
Module 2: Data Science Libraries
- Functions
- NumPy — arrays, operations
- Pandas — DataFrames, data cleaning, aggregation
- Matplotlib & Seaborn — visualization
- Exploratory Data Analysis (EDA) hands-on
Module 3: ML Fundamentals + Data Preprocessing
- AI vs ML vs Deep Learning
- Types of ML, ML lifecycle
- Handling missing values, encoding, feature scaling
- Outlier detection, train/test split
Module 4: Supervised Learning
- Linear & Logistic Regression
- KNN, SVM
- Decision Trees, Random Forest, XGBoost
- Hands-on project: Customer Churn / Disease Prediction
Module 5: Unsupervised Learning + Model Evaluation
- K-Means Clustering, PCA
- Accuracy, Precision, Recall, F1, ROC-AUC
- Confusion matrix, Cross-validation
- Hyperparameter tuning (GridSearchCV)
Module 6: Deep Learning Basics
- Neural Networks — neurons, layers, activation functions
- Backpropagation (conceptual)
- TensorFlow / Keras — build & train models
- CNN basics for image tasks, intro to transfer learning
Module 7: NLP + Transformer Foundations
- Text preprocessing — tokenization, stemming, lemmatization
- Bag of Words, TF-IDF, Word Embeddings
- Transformer architecture & attention mechanism
- BERT vs GPT — conceptual differences
Module 8: LLMs + Prompt Engineering
- How LLMs work — pre-training, fine-tuning, RLHF
- Key models — GPT-4, Gemini, Claude, LLaMA, Mistral
- Tokens, context windows, temperature, top-p
- Zero-shot, few-shot, chain-of-thought prompting
- Prompt engineering best practices
Module 9: OpenAI API + Gemini API
- API setup and authentication
- Chat Completions — system/user/assistant roles
- Streaming responses, Function calling / Tool use
- Vision API — image understanding
- Embeddings API, cost management
Module 10: LangChain + RAG + Vector Databases
- LangChain — chains, prompt templates, memory, agents
- What are vector embeddings
- Vector DBs — ChromaDB, FAISS, Pinecone
- Building a full RAG pipeline
- Querying PDFs, web pages, and text documents
Module 11: Backend API Development with FastAPI
- Introduction to FastAPI
- Creating REST endpoints
- Integrating ML/LLM models into APIs
- Request validation with Pydantic
- Async API calls, API authentication (Keys + JWT basics)
Module 12: Building GenAI Applications
- AI Chatbot with memory and context
- Document Q&A app (RAG-based)
- AI summarizer and content generator
- Streamlit UI for rapid app building
Module 13: Fine-Tuning + Advanced GenAI
- Fine-tuning with OpenAI API
- Hugging Face — models, datasets, tokenizers
- Running open-source LLMs locally (Ollama)
- LoRA / QLoRA — parameter-efficient fine-tuning
- Multi-agent systems with LangGraph / CrewAI
Module 14: Deployment & MLOps Basics
- Deploying ML models with FastAPI
- Deploying GenAI apps on Render / Railway / AWS
- Dockerizing AI applications
- Environment & secrets management
- Monitoring, rate limiting, caching, CI/CD basics
Module 15: Capstone Projects
- Project 1 — ML Project: Customer Churn Prediction deployed via FastAPI
- Project 2 — GenAI Project : AI Document Assistant (chat with PDFs, deployed on cloud)
- Project 3 — Full-Stack AI Project : Multi-Agent Research Tool with Streamlit UI
Certification
Course Certification:
Upon successful completion of the course, there will be cumulative test conducted and students who scored above 60% marks will receive a certificate of completion from GeekBase Technology, which can be used to showcase their newly acquired Artificial-intelligence skills.
Note: Test will be a MCQ pattern and maximum two attempts allowed.
Why certified Airtificial Intelligence ?
