Machine Learning for Image Analysis

Catalog description

This course explores the theoretical foundations and practical applications of machine learning in image processing, thus enabling students to tackle real-world problems through cutting-edge image analysis projects. The course will introduce the fundamentals of machine learning methods suitable for image analysis. The student will be exposed to (1) machine learning basics, including supervised, unsupervised, and deep learning techniques, and their adaptation to image data; (2) theoretical underpinnings of deep neural networks, including feedforward and convolutional neural networks (CNNs), recurrent neural networks (RNNs), and autoencoders, and understand how to leverage them for image classification, object detection, image segmentation, and video analysis; (3) deep learning optimization algorithms, optimization challenges, and the role of hyperparameters tuning; (4) Gaussian processes and posterior inference; (5) advanced computer vision tasks, including image recognition, object detection, and localization; (6) semantic and instance segmentation, and their applications in understanding image content at a pixel-level; and (7) practical implementation of deep learning models for image analysis using popular programming frameworks, such as TensorFlow and PyTorch.