Course Duration: 12 Weeks

What you'll learn

Build and deploy a fully functional, production-ready AI and ML application, and Equip learners with the skills to contribute to or lead AI and ML projects confidently.

Foundations of AI and ML

• What is AI? What is ML between AI, ML?
• Differences, and Deep Learning
• Real-world applications of AI/ML
• Overview of supervised, unsupervised, and reinforcement learning
• Setting up the Python environment (Jupyter, Anaconda)
• Introduction to Python basics (syntax, variables, data types)

Mathematical Foundations I - Linear Algebra Basics

• Vectors, matrices, and matrix operations
• Dot product and matrix multiplication
• Applications in AI/ML (e.g., representation of data)
• Matrix operations in Python using NumPy
• Simple examples of data representation in matrices

Mathematical Foundations II – Probability and Statistics

• Basics of probability (independence, conditional probability, Bayes' theorem)
• Descriptive statistics (mean, median, mode, variance, standard deviation)
• Introduction to distributions (normal, uniform)
• Calculating probabilities and descriptive statistics in Python using libraries like SciPy and pandas

Mathematical Foundations III – Calculus for ML

• Basics of differentiation (derivatives, chain rule)
• Gradient and optimization concepts.
• Basics of integration and its role in probability (continuous distributions)
• Gradient descent algorithm overview
• Using Python to compute derivatives and gradients (SymPy or NumPy)
• Visualizing functions and their gradients with Matplotlib

Introduction to Machine Learning

• Key concepts: features, labels, training, testing, and validation
• Overview of the ML workflow.
• Introduction to simple algorithms (linear regression)
• Implementing linear regression using Python (from scratch and using scikit-learn)

Data Handling and Preprocessing

• Importance of data in ML
• Handling missing data, outliers, and normalization
• Data visualization (plots, histograms, scatter plots)
• Preprocessing datasets using pandas and scikit-learn
• Visualizing data using Matplotlib and Seaborn

Supervised Learning I – Classification

• Introduction to classification (decision trees, k-NN)
• Performance metrics: accuracy, precision, recall, F1 score
• Implementing a decision tree classifier using scikit-learn
• Evaluating a model with performance metrics

Supervised Learning II – Advanced Algorithms

• Support Vector Machines (SVM)
• Logistic regression
• Building and evaluating SVM and logistic regression models in scikit-learn

Unsupervised Learning

• Introduction to clustering (k-means)
• Dimensionality reduction (PCA)
• Applying k-means clustering and PCA on real-world datasets

Introduction to Neural Networks

• Basics of neural networks (perceptron, activation functions)
• Role of calculus in backpropagation (gradient descent, partial derivatives)
• Importance of optimization in training neural networks
• Implementing a simple neural network using Python (from scratch)
• Using TensorFlow or PyTorch for basic neural network training

AI Ethics and Applications

• Ethical concerns in AI/ML
• Bias, fairness, and transparency in models
• Future trends in AI/ML
• Analyzing ethical concerns in a sample dataset

Capstone Project

• Students work on a small project of their choice, such as
• Presenting findings and reflecting on the entire learning process