Artificial Intelligence

COURSE DESCRIPTIOn

 

📍 Module 1: Introduction to Python for Machine

Learning

🕒 Duration: 1-2 Weeks

Theory

• Introduction to Python for ML
• Installing Python and Jupyter Notebook
• Data types, Variables, and Operators
• Conditional Statements and Loops
• Functions and Modules
• NumPy for numerical computing
• Pandas for data manipulation
• Matplotlib & Seaborn for data visualization

Code

• Writing Python scripts
• Handling datasets with Pandas
• Visualizing datasets

Fun Project 🎯

“Data Explorer”: Build a simple Python script that loads a dataset, performs basic data

analysis, and generates visualizations.

📍 Module 2: Foundations of Machine Learning

🕒 Duration: 1 WeekTheory

• What is Machine Learning?
• Supervised vs Unsupervised Learning
• Overview of Regression & Classification
• The ML Pipeline: Data Collection, Preprocessing, Model Training, Evaluation

Code

• Implementing Linear Regression from scratch
• Using Scikit-learn for simple ML tasks

Fun Project 🎯

“Predict House Prices”: Train a simple Linear Regression model to predict house prices from

features like square footage and number of rooms.

📍 Module 3: Data Preprocessing & Feature Engineering

🕒 Duration: 1 Week

Theory

• Handling missing values
• Feature scaling and normalization
• One-hot encoding & label encoding
• Feature selection techniques

Code

• Implementing feature engineering using Scikit-learn
• Handling categorical and numerical data

Fun Project 🎯

“Titanic Survivor Prediction”: Process the Titanic dataset, engineer features, and train a

classifier to predict survival.

📍 Module 4: Supervised Learning – Regression Models🕒 Duration: 1-2 Weeks

Theory

• Simple & Multiple Linear Regression
• Polynomial Regression
• Ridge & Lasso Regression
• Evaluation Metrics (MSE, RMSE, R² Score)

Code

• Implement regression models in Scikit-learn
• Implement Ridge and Lasso from scratch

Fun Project 🎯

“Stock Price Prediction”: Use regression to predict stock prices based on historical data.

📍 Module 5: Supervised Learning – Classification Models

🕒 Duration: 1-2 Weeks

Theory

• Logistic Regression
• k-Nearest Neighbors (k-NN)
• Support Vector Machines (SVM)
• Decision Trees & Random Forest
• Model evaluation (Confusion Matrix, Precision, Recall, F1-Score, AUC-ROC)

Code

• Train and compare different classifiers
• Implement SVM and Decision Trees from scratch

Fun Project 🎯

“Spam Email Detector”: Build a classifier to detect spam emails.📍 Module 6: Unsupervised Learning – Clustering &

Dimensionality Reduction

🕒 Duration: 1-2 Weeks

Theory

• k-Means Clustering
• Hierarchical Clustering
• Principal Component Analysis (PCA)
• t-SNE for visualization

Code

• Implement clustering algorithms in Python
• Reduce dataset dimensions with PCA

Fun Project 🎯

“Customer Segmentation”: Cluster customers based on shopping patterns.

📍 Module 7: Neural Networks & Deep Learning

🕒 Duration: 2 Weeks

Theory

• Introduction to Deep Learning
• Basics of Artificial Neural Networks (ANN)
• Activation Functions
• Backpropagation & Gradient Descent
• Introduction to TensorFlow & PyTorch

Code

• Implement an ANN using TensorFlow/Keras
• Train a deep learning model

Fun Project 🎯

“Handwritten Digit Recognition”: Train an ANN to recognize digits from the MNIST dataset.📍 Module 8: Convolutional Neural Networks (CNNs)

🕒 Duration: 2 Weeks

Theory

• What are CNNs?
• Convolutional layers, Pooling layers
• Transfer Learning

Code

• Train a CNN from scratch using TensorFlow/Keras
• Use pre-trained models like VGG16 & ResNet

Fun Project 🎯

“Build an Image Classifier”: Train a CNN to classify images of cats and dogs.

📍 Module 9: Recurrent Neural Networks (RNNs) & NLP

🕒 Duration: 2 Weeks

Theory

• Introduction to NLP
• Word Embeddings (Word2Vec, GloVe)
• LSTMs & GRUs

Code

• Build an RNN for text generation
• Implement LSTM for sentiment analysis

Fun Project 🎯

“AI Chatbot”: Build a chatbot using LSTMs.📍 Module 10: Generative Adversarial Networks (GANs)

🕒 Duration: 2 Weeks

Theory

• What are GANs?
• Generator vs Discriminator
• Training GANs

Code

• Implement a simple GAN from scratch
• Train a GAN to generate images

Fun Project 🎯

“Create AI Art”: Train a GAN to generate realistic images.

📍 Final Capstone Project: Build a Complete ML

Application

🕒 Duration: 2 Weeks

• Choose a problem (e.g., face recognition, fraud detection, AI music generator)
• Collect and preprocess data
• Train and optimize a model
• Deploy the model as a web application using Flask/Django

📍 Bonus Topics

💡 (Optional for Enthusiasts!)

• Reinforcement Learning
• AutoML
• Explainable AI
• AI Ethics🔹 Course Outcome

By the end of this course, students will:

✅ Master Machine Learning concepts from scratch

✅ Build & deploy real-world ML applications

✅ Understand Deep Learning & Generative AI

✅ Be ready for jobs in AI & Data Science