- KHDA
- AIAL
- Royal Institute for Chartered Engineer - RICE (USA)
Course Info
Key Highlights
Target Audience
Final Capstone Project
Choose a real-world problem in any domain (finance, healthcare, robotics, etc.) and build an AI model to solve it.
Present findings, model performance, and future improvements.
Assessment Methods
Quizzes at the end of each module
Hands-on projects and assignments
Final capstone project presentation
Module 1: Introduction to Python and AI Fundamentals
1.1 Introduction to AI and Python's Role AI Development
Overview of AI applications in real-world problems.
Python libraries for AI (NumPy, Pandas, SciPy)
Setting up the environment (Anaconda, Jupyter Notebooks)
1.2 Python Basics for AI
Data types, loops, conditions, and functions
Object-oriented programming (OOP) essentials
Introduction to NumPy for efficient computations
Hands-on Project: Build a simple AI-based chatbot
Module 2: Data Handling and Preprocessing
2.1 Data Wrangling with Pandas
Working with datasets
Data cleaning and preparation
2.2 Data Visualization
Introduction to Matplotlib and Seaborn
Plotting and visualizing trends and relationships in data
2.3 Feature Engineering
Handling missing data
Feature scaling and normalization
Hands-on Project: Create an AI-ready dataset from raw data (e.g., sales or medical records)
Module 3: Machine Learning with Python
3.1 Introduction to Machine Learning
Types of ML: Supervised, Unsupervised, Reinforcement Learning
Introduction to Scikit-Learn
3.2 Regression Algorithms
Linear Regression
Decision Trees and Random Forest
3.3 Classification Algorithms
Logistics Regression
K-Nearest Neighbors (k-NN)
Support Vector Machines (SVM)
3.4 Clustering Algorithms
k-Means Clustering
Hierarchical Clustering
Hands-on Project: Develop a machine learning model to predict house prices or classify medical data
Module 4: Deep Learning with Python
4.1 Introduction to Neural Networks
Perception, activation functions, and forward/backpropagation
Introduction to TensorFlow and Keras
4.2 Building Deep Learning Models
Multi-layer perceptions (MLPs)
Hyperparameter tuning and optimization
4.3 Convolutional Neural Networks (CNNs)
CNN architecture for image processing
Applications in computer vision
4.4 Lesson 4.4: Recurrent Neural Networks (RNNs)
Time series and sequence prediction
Long Short-Term Memory (LSTM) networks
Hands-on Project: Build a deep learning model for image classification (e.g., handwritten digits recognition) or text classification (e.g., sentiment analysis)
Module 5: AI in Natural Language Processing (NLP)
5.1: NLP Basics and Text Preprocessing
Tokenization, stemming, and lemmatization
Word embeddings (TF-IDF, Word2Vec)
5.2: Sentiment Analysis and Text Classification
Building text classification models
Sentiment analysis with Scikit-Learn and TensorFlow
5.3: Chatbots and NLP Applications
Building simple AI-based chatbots with NLP processing
Neural network models for NLP (transformers, GPT)
Hands-on Project: Develop an AI-based sentiment analysis tool or chatbot
Module 6: AI in Computer Vision
6.1: Introduction to Computer Vision
Image processing techniques (OpenCV, PIL)
Basic image transformations and filters
6.2: Object Detection and Recognition
Applying CNNs for object recognition
Transfer learning and pre-trained models (VGG, ResNet)
Hands-on Project: Build an AI-based object detection system