Level 2 class: In this level, students will explore Computer Vision, a dynamic field of AI that enables machines to interpret and understand visual data. They will learn how computers analyze images and videos to perform tasks such as object detection, image classification, facial recognition, and scene analysis. Through hands-on exercises using libraries like OpenCV, students will build applications that can “see” and respond to their environment. This module balances foundational theory with practical implementation, helping learners understand how vision-based AI powers real-world technologies such as self-driving cars, medical diagnostics, and augmented reality. In Level 3 class, In the third level, students will focus on the core principles of Machine Learning (ML), using industry-standard libraries such as TensorFlow, Keras, NumPy, and essential visualization tools. They will learn how machines identify patterns and make data-driven decisions through both supervised and unsupervised learning techniques. Key topics include model training, optimization, and performance evaluation. Students will build and experiment with neural networks for tasks like classification and prediction, gaining hands-on experience in developing and refining ML models.