Artificial Intelligence and Machine Learning Course
Duration: 6 Months / 24 Weeks
Level: Beginner to Job-Ready
Suggested Schedule: 5–6 days per week
Technologies: Python, SQL, NumPy, Pandas, Matplotlib, Scikit-learn, TensorFlow, OpenCV, NLP, Generative AI, Flask/Streamlit and GitHub
Level: Beginner to Job-Ready
Suggested Schedule: 5–6 days per week
Technologies: Python, SQL, NumPy, Pandas, Matplotlib, Scikit-learn, TensorFlow, OpenCV, NLP, Generative AI, Flask/Streamlit and GitHub
Month 1: Python Programming and Data Foundations
- Introduction to Artificial Intelligence
- AI, Machine Learning, Deep Learning and Generative AI
- Real-world AI applications
- Installing Python, Anaconda and VS Code
- Google Colab and Jupyter Notebook
- Variables and data types
- Input and output
- Operators
- Conditional statements
- Loops
Practical: Calculator, grade analyser and salary calculator.
- Strings and string operations
- Lists, tuples, sets and dictionaries
- Functions and parameters
- Return values
- Lambda functions
- List comprehensions
- Modules and packages
- Date and time handling
- Exception handling
- Debugging techniques
Mini-project: Student performance management system.
- Classes and objects
- Constructors
- Encapsulation
- Inheritance
- Polymorphism
- File reading and writing
- CSV and JSON files
- Virtual environments
- Installing packages using pip
- Introduction to Git and GitHub
Mini-project: Inventory and file-based reporting system.
- Scalars, vectors and matrices
- Matrix operations
- Mean, median and mode
- Variance and standard deviation
- Quartiles and interquartile range
- Probability fundamentals
- Probability distributions
- Normal distribution
- Correlation and covariance
- Hypothesis testing fundamentals
- Gradient and derivative concepts
Practical: Statistical analysis of student or sales data.
Month 2: Data Analytics and Data Visualisation
- NumPy arrays
- Array creation and indexing
- Slicing and reshaping
- Mathematical operations
- Broadcasting
- Aggregation functions
- Random number generation
- Matrix operations
- Handling missing values
- NumPy performance benefits
Mini-project: Numerical sales-data analyser.
- Series and DataFrame
- Loading CSV and Excel files
- Data inspection
- Selecting and filtering records
- Sorting and grouping
- Handling missing values
- Removing duplicates
- Data-type conversion
- Merging and joining datasets
- Pivot tables
- Date and time data
- Feature creation
Mini-project: Customer and sales-data cleaning system.
- Matplotlib fundamentals
- Line, bar and scatter charts
- Histograms and box plots
- Pie charts
- Seaborn fundamentals
- Heatmaps
- Pair plots
- Distribution plots
- Dashboard design principles
- Identifying patterns and outliers
- Storytelling with data
Project: Exploratory data analysis dashboard.
- Database fundamentals
- Creating databases and tables
- SQL CRUD operations
- Filtering and sorting
- Aggregate functions
- Grouping
- Joins
- Subqueries
- Views
- Window-function concepts
- Connecting Python to databases
- Extracting SQL data using Pandas
Project: Business sales analysis using Python and SQL.
Month 3: Machine Learning
- Types of machine learning
- Supervised and unsupervised learning
- Features and target variables
- Training and testing data
- Data preprocessing
- Categorical-data encoding
- Feature scaling
- Handling missing values
- Outlier detection
- Scikit-learn pipelines
- Bias and variance
- Overfitting and underfitting
- Simple linear regression
- Multiple linear regression
- Polynomial regression
- Decision tree regression
- Random forest regression
- Regression evaluation: MAE
- Regression evaluation: MSE
- Regression evaluation: RMSE
- Regression evaluation: R² score
- Residual analysis
- Feature importance
Mini-project: House-price or sales-forecasting system.
- Logistic regression
- K-Nearest Neighbours
- Decision tree
- Random forest
- Support Vector Machine
- Naive Bayes
- Confusion matrix
- Accuracy
- Precision
- Recall
- F1-score
- ROC-AUC
- Handling imbalanced datasets
Project: Loan-default or customer-churn prediction.
- Introduction to clustering
- K-Means clustering
- Hierarchical clustering
- DBSCAN concepts
- Selecting the number of clusters
- Elbow method
- Silhouette score
- Principal Component Analysis
- Dimensionality reduction
- Anomaly detection
- Association-rule fundamentals
Project: Customer segmentation system.
Month 4: Advanced Machine Learning and Deep Learning
- Cross-validation
- K-Fold and Stratified K-Fold
- Grid Search
- Randomized Search
- Hyperparameter tuning
- Feature selection
- Feature engineering
- Ensemble learning
- Bagging and boosting
- AdaBoost
- Gradient Boosting
- XGBoost or LightGBM introduction
- Explainable AI
- Feature importance
- SHAP and LIME concepts
Project: Explainable credit-risk prediction.
- Artificial neural networks
- Biological and artificial neurons
- Perceptron
- Activation functions
- Forward propagation
- Loss functions
- Backpropagation
- Gradient descent
- Optimizers
- Epoch, batch size and learning rate
- TensorFlow and Keras
- Building a neural network
- Preventing overfitting
- Dropout and regularization
Mini-project: Customer-churn prediction with ANN.
- Introduction to computer vision
- Image representation
- Loading and processing images
- OpenCV fundamentals
- Image resizing and colour conversion
- Contours
- Thresholding and edge detection
- Image augmentation
- Convolutional Neural Networks
- Convolution and pooling layers
- Image classification
- Transfer learning fundamentals
Project: Plant-disease, waste or product-image classifier.
- Face detection
- Object detection concepts
- Haar Cascade
- MediaPipe fundamentals
- YOLO introduction
- Image annotation
- Real-time webcam processing
- Model performance evaluation
- Object tracking concepts
- Model deployment considerations
Project: Driver-drowsiness or safety-helmet detection system.
Month 5: NLP and Generative AI
- Introduction to NLP
- Text cleaning
- Tokenization
- Stop-word removal
- Stemming and lemmatization
- Bag of Words
- N-grams
- TF-IDF
- Text vectorisation
- Sentiment analysis
- Text classification
- Evaluation of NLP models
Project: Customer-review sentiment analyser.
- Word embeddings
- Word2Vec and GloVe concepts
- Recurrent Neural Networks
- LSTM and GRU concepts
- Sequence modelling
- Attention mechanism
- Transformer architecture
- BERT fundamentals
- Hugging Face introduction
- Pretrained NLP models
Project: Spam, fake-news or support-ticket classifier.
- Introduction to Generative AI
- Large Language Models
- Tokens and context windows
- Transformer-based language models
- Prompt engineering
- Zero-shot and few-shot prompting
- Role and instruction prompting
- Structured output
- Hallucinations and limitations
- Responsible AI
- Text and image-generation concepts
- Using an LLM API securely
Mini-project: AI content and question generator.
- Embeddings
- Semantic search
- Vector database concepts
- Document loading and chunking
- Retrieval-Augmented Generation
- RAG workflow
- Building a question-answering system
- Conversation memory concepts
- Tool and function calling
- LangChain or equivalent framework
- Evaluating RAG responses
- Protecting sensitive data
Project: AI chatbot for PDF or company documents.
Month 6: Deployment, MLOps and Final Project
- Introduction to Streamlit
- Creating interactive AI interfaces
- Uploading CSV and image files
- Displaying predictions
- Creating charts and dashboards
- Flask or FastAPI fundamentals
- Creating prediction APIs
- Connecting a model with a web interface
- Input validation and error handling
Project: Deployable AI prediction application.
- Saving models with Pickle and Joblib
- Model versioning
- Data and model pipelines
- Logging and monitoring concepts
- Docker fundamentals
- Environment variables
- API testing with Postman
- Cloud deployment concepts
- Model drift
- Retraining workflows
- Performance and security considerations
- Problem identification
- Dataset selection
- Literature review
- Data collection
- Data cleaning
- Exploratory data analysis
- Feature engineering
- Algorithm selection
- Model training
- Hyperparameter tuning
- Model evaluation
- Explainable AI
- Front-end development
- API integration
- Final testing and debugging
- Model deployment
- GitHub repository preparation
- Technical documentation
- Project report
- Presentation and demonstration
- AI resume preparation
- Creating a project portfolio
- AI and ML interview questions
- Mock technical interview
- Final project review
Suggested Final Projects
- AI-Based Driver Drowsiness Detection
- AI PCB Fault Diagnosis and Repair Recommendation
- Loan Default Prediction System
- Customer Churn Prediction
- Plant Disease Detection
- AI-Based Medical Appointment Assistant
- Sales and Demand Forecasting
- Resume Ranking and Job Recommendation
- Flood-Risk Prediction Using Weather Data
- AI-Powered Cyber Threat Detection
- PDF Question-Answering RAG Chatbot
- E-Waste Classification and Repairability Prediction
Assessment Structure
| Assessment | Weightage |
|---|---|
| Weekly practical assignments | 15% |
| Python and data-analysis project | 10% |
| Machine-learning project | 15% |
| Deep-learning project | 15% |
| NLP or Generative AI project | 15% |
| Final capstone project | 25% |
| Attendance and presentation | 5% |
Course Outcomes
After completing this course, students will be able to:
- Develop AI applications using Python.
- Clean, analyse and visualise real-world datasets.
- Apply statistical methods to data.
- Build regression, classification and clustering models.
- Evaluate, tune and explain machine-learning models.
- Develop neural networks and computer-vision systems.
- Build NLP and text-classification applications.
- Create Generative AI and RAG-based assistants.
- Develop prediction APIs and AI web applications.
- Deploy trained models.
- Manage AI projects using Git and GitHub.
- Build a job-ready AI project portfolio.
Required Software
- Python 3.x
- Anaconda or Miniconda
- Visual Studio Code
- Jupyter Notebook
- Google Colab
- MySQL
- Git and GitHub
- Postman
- TensorFlow and Keras
- Scikit-learn
- OpenCV
- Streamlit
- Flask or FastAPI
- Hugging Face libraries
Recent Post
