Deep Learning for Computer Vision: Techniques & Applications

О курсе

Master modern computer vision through a practical, PyTorch‑first path. In this course you will build, train, and evaluate deep neural networks to solve real‑world image problems. You’ll begin with the end‑to‑end ML workflow and a simple multilayer perceptron (MLP), then learn the core building blocks of convolutional neural networks (CNNs): convolution, pooling, feature maps, and activation functions. From there, you’ll implement and fine‑tune state‑of‑the‑art architectures such as VGG and ResNet, and practice best‑practice model evaluation. You will then tackle object detection and localization with YOLO, SSD, and Faster R‑CNN, and progress to image segmentation with U‑Net and Mask R‑CNN. Along the way you’ll use PyTorch to perform data augmentation, hyperparameter tuning, and non‑maximum suppression while balancing accuracy, speed, and deployment constraints. Designed for learners with basic Python and NumPy, this course is ideal for aspiring machine‑learning engineers, data scientists, and developers who want industry‑ready experience with CNNs, transfer learning, object detection, and image segmentation. Build a portfolio‑quality project and gain in‑demand skills for AI‑powered products. Expect clear code templates and real datasets for practice and reproducible workflows.

Навыки, которые вы освоите

Учитесь у экспертов

Aamna Mohammed Al Shehhi

Assistant Professor