Advanced Applied Deep Learning
Resources
Sheng Yun Wu
Resources
Sheng Yun Wu
Here are some valuable resources to support the Advanced Applied Deep Learning: Convolutional Neural Networks (CNNs) and Object Detection course:
"Advanced Applied Deep Learning: Convolutional Neural Networks and Object Detection" by Umberto Michelucci
This book covers advanced topics in deep learning with a focus on CNNs and object detection techniques like R-CNN, YOLO, and SSD. Link on Springer
"Deep Learning" by Ian Goodfellow, Yoshua Bengio, and Aaron Courville
This comprehensive book explains the fundamentals of deep learning, including CNNs, RNNs, and more advanced architectures. Official Book Website
"Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow" by Aurélien Géron
A practical book to implement machine learning and deep learning projects, including CNNs and object detection models with TensorFlow and Keras. Link on O'Reilly
Deep Learning Specialization on Coursera by Andrew Ng (deeplearning.ai)
This course offers an in-depth understanding of deep learning, including CNNs, object detection, and transfer learning. Course Link
Convolutional Neural Networks (CNN) with TensorFlow by DeepLearning.AI on Coursera
Focuses specifically on CNNs and their applications in computer vision. Course Link
YOLO Object Detection from Scratch using PyTorch on Udemy
A hands-on course teaching how to build YOLO object detection models using PyTorch. Course Link
PyTorch CNN Tutorial: A step-by-step guide on implementing CNNs using PyTorch. Tutorial Link
TensorFlow Object Detection API: A comprehensive guide for implementing state-of-the-art object detection models using TensorFlow. Guide Link
YOLOv5 Documentation: Learn how to use the YOLOv5 object detection model, which is widely used for real-time applications. YOLOv5 GitHub
"ImageNet Classification with Deep Convolutional Neural Networks" by Alex Krizhevsky, Ilya Sutskever, and Geoffrey Hinton
This is the seminal paper that popularized CNNs by winning the ImageNet competition. Paper Link
"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks" by Shaoqing Ren, Kaiming He, Ross B. Girshick, and Jian Sun
A breakthrough paper that introduced Faster R-CNN for efficient object detection. Paper Link
"YOLOv4: Optimal Speed and Accuracy of Object Detection" by Alexey Bochkovskiy, Chien-Yao Wang, and Hong-Yuan Mark Liao
A detailed exploration of the YOLO architecture for real-time object detection. Paper Link
YOLOv5 Object Detection
Ultralytics' YOLOv5 is one of the most widely used real-time object detection models. It is open source, easy to train, and deployable on real-time systems. GitHub Link
TensorFlow Models for Object Detection
This repository contains code to train, test, and deploy various object detection models including Faster R-CNN, SSD, and more. GitHub Link
These resources should give you a solid foundation for your Advanced Applied Deep Learning course, covering both theoretical knowledge and hands-on projects.