Artificial Intelligence and Machine Learning Essentials

This three-day course covers essential AI and ML concepts, deep learning fundamentals, and hands-on model development using Python. Participants will explore both theoretical and practical aspects of AI and ML, with a focus on real-world applications and model building.

To equip PhD scholars and academicians with foundational and practical skills in artificial intelligence (AI) and machine learning (ML). This course aims to provide a comprehensive understanding of AI and ML concepts, introduce deep learning frameworks, and offer hands-on experience in developing ML models.

Day 1: Introduction to AI and ML Concepts

• Overview of AI and ML
  • History and evolution of AI and ML
  • Current trends and future directions
• Supervised vs Unsupervised Learning
  • Key differences and use cases
  • Common algorithms and applications
• Introduction to Algorithms
  • Overview of essential AI/ML algorithms (e.g., Decision Trees, K-Means)
  • Understanding algorithm selection and performance evaluation

Day 2: Deep Learning and Neural Networks

• Basics of Neural Networks
  • Structure of neural networks: Layers, neurons, and activation functions
  • Introduction to backpropagation and gradient descent
• Introduction to TensorFlow and PyTorch
  • Overview of popular deep learning frameworks
  • Practical exercises on building simple neural networks
• Practical Examples and Exercises
  • Hands-on exercises with real-world datasets
  • Building and training neural networks from scratch

Day 3: Hands-on Session

• Creating a Machine Learning Model in Python
  • Step-by-step guide to building a machine learning model
  • Data preprocessing, model selection, training, and evaluation
• Capstone Project: Model Development
  • Developing a complete ML model using Python
  • Presenting findings and discussing challenges

Data scientists, AI/ML enthusiasts, computer science students, researchers, and academicians.