4-days Instructor-led

Course Description 

This 4-day Artificial Intelligence (AI) course introduces participants to the fundamental techniques and practical tools used to develop AI-driven solutions. Blending theory with applied labs, the course walks learners through the AI pipeline—data preparation, model development, neural networks, and real-world applications. Participants will work with Python, scikit-learn, and TensorFlow to build, test, and deploy machine learning models, gaining the practical experience needed to apply AI in a business or technical setting. 

Key Takeaways 

• Explore the foundations and use cases of AI across industries 

• Build and evaluate machine learning models using Python 

• Use scikit-learn for classic models and TensorFlow for neural networks 

• Apply natural language processing techniques to real data 

• Translate problem statements into AI solutions using structured workflows 

• Gain hands-on experience through guided labs and mini-projects 

Prerequisites 

• Basic programming experience (preferably in Python) 

• Familiarity with core mathematical and statistical concepts 

• No prior AI experience required, but a technical background is recommended 

Module 1: Introduction to AI and Core Concepts 

• What is Artificial Intelligence? Definitions, Goals, and Applications 

• History of AI: Rule-based Systems to Deep Learning 

• Types of AI: Narrow AI, General AI, and Machine Learning 

• Overview of Supervised vs. Unsupervised Learning 

• Introduction to Python Libraries for AI (NumPy, Pandas, scikit-learn) 

• Hands-On Lab: Explore datasets and create your first machine learning model with scikit-learn 

Module 2: Supervised Learning Techniques and Model Development 

• Data Cleaning, Preparation, and Feature Engineering 

• Supervised Learning Algorithms: 

• Linear Regression 

• Decision Trees 

• Support Vector Machines 

• K-Nearest Neighbors 

• Model Evaluation Metrics: Accuracy, Precision, Recall, F1 Score 

• Train-Test Splits and Cross-Validation 

• Hands-On Lab: Develop, train, and evaluate multiple supervised learning models 

Module 3: Neural Networks and Deep Learning with TensorFlow 

• Fundamentals of Neural Networks and Deep Learning 

• Introduction to TensorFlow and Keras APIs 

• Activation Functions, Loss Functions, and Optimizers 

• Building Feedforward Neural Networks 

• Overfitting, Dropout, and Model Tuning Techniques 

• Hands-On Lab: Build and train a neural network for image or text classification 

Module 4: Applied AI and Capstone Project 

• Natural Language Processing (NLP) Basics 

• Tokenization, Embeddings, and Sentiment Analysis 

• AI in Practice: Case Studies in Healthcare, Finance, and Retail 

• Ethics, Bias, and Limitations in AI Systems 

• AI Deployment Concepts: Saving Models and Making Predictions