This course provides a solid foundation in Artificial Intelligence, covering AI concepts, Python programming, data preprocessing, mathematics for AI, machine learning, and neural networks. Through theory and a hands-on mini project, students will learn to build and evaluate AI models and apply them to real-world problems while understanding ethical considerations.
Course Modules
Module 1: Introduction to Artificial Intelligence
- Definition, scope, and objectives of AI
- History and evolution of AI
- Real-world applications across industries
- Differences between AI, Machine Learning, and Deep Learning
- Ethical considerations and responsible AI practices
- Overview of AI systems and components
Module 2: Python Programming for Artificial Intelligence
- Python fundamentals: variables, data types, operators, and control structures
- Functions and modular programming
- Python modules and packages relevant to AI
- Introduction to AI libraries: NumPy, Pandas, Matplotlib
- Loading, inspecting, and manipulating datasets in Python
Module 3: Data Handling and Preprocessing
- Structured vs unstructured data
- Data collection, cleaning, and standardization
- Handling missing or inconsistent data
- Normalization, transformation, and feature selection
- Preparing datasets for AI and machine learning models
Module 4: Mathematics and Statistics for AI
- Linear algebra essentials: vectors, matrices, operations
- Probability concepts and distributions
- Descriptive statistics: mean, median, variance, standard deviation
- Data visualization techniques for understanding datasets
- Applying mathematical principles in AI algorithms
Module 5: Machine Learning Fundamentals
- Introduction to machine learning concepts
- Supervised and unsupervised learning
- Regression, classification, and clustering techniques
- Training, validation, and testing datasets
- Model evaluation metrics: accuracy, precision, recall, F1-score
- Overview of dimensionality reduction
Module 6: Neural Networks and Mini AI Project
- Fundamentals of neural networks and perceptron models
- Network architecture: neurons, layers, weights, and activation functions
- Training basics: forward propagation, loss function, gradient descent
- Mini AI project: dataset selection, preprocessing, model building, evaluation, and result interpretation
Learning Outcomes
By the end of this programme, learners will be able to:
- Understand key concepts, applications, and ethical considerations of Artificial Intelligence.
- Write Python programs and leverage AI libraries for data handling and model development.
- Preprocess and transform structured and unstructured data for AI tasks.
- Apply mathematical and statistical principles in AI and machine learning models.
- Build, evaluate, and interpret basic machine learning models (regression, classification, clustering).
- Understand neural network fundamentals and implement a mini AI project using real-world data.
