Convolutional Neural Networks is an essential course for those interested in computer vision and deep learning. Throughout the four modules, you will gain a deep understanding of the evolution and applications of computer vision, including autonomous driving, face recognition, and more. The course covers the foundations of convolutional neural networks, deep convolutional models, object detection, and special applications such as face recognition and neural style transfer. By the end, you will be equipped to build convolutional neural networks, understand case studies, and apply these techniques to a variety of image, video, and 2D or 3D data.
The course is designed to provide a pathway for learners to understand the capabilities, challenges, and consequences of deep learning, preparing them to participate in the development of leading-edge AI technology. Throughout the modules, you will gain the knowledge and skills to apply machine learning to your work, level up your technical career, and take a definitive step in the world of AI.
Certificate Available ✔
Get Started / More Info
The course comprises four modules that cover the foundations of convolutional neural networks, deep convolutional models, object detection, and special applications like face recognition and neural style transfer.
This module introduces the foundations of convolutional neural networks, covering topics such as computer vision, edge detection, padding, strided convolutions, pooling layers, and more. You will also gain insights into the basics of ConvNets and build a convolutional model step by step.
In this module, you will explore deep convolutional models through case studies, including classic networks, ResNets, Inception Network, MobileNet, EfficientNet, and transfer learning. You will also delve into data augmentation and the state of computer vision.
The third module focuses on object detection, covering topics such as object localization, bounding box predictions, YOLO algorithm, semantic segmentation with U-Net, and more. You will also learn about detection algorithms and gain practical experience in car detection and image segmentation.
This module delves into special applications of convolutional neural networks, including face recognition and neural style transfer. You will explore concepts such as one shot learning, Siamese Network, triplet loss, and cost functions for neural style transfer, providing a comprehensive understanding of these advanced applications.
Machine Learning for Supply Chains equips students with the skills to use machine learning techniques for analyzing and predicting product usage within supply chains....
Identify Damaged Car Parts with Vertex AutoML Vision
Predict Ad Clicks Using Logistic Regression and XG-Boost
ChatGPT Prompt Engineering for Developers is a short course teaching how to use large language models (LLMs) to build new applications, engineer effective prompts,...