Oreilly - Practical Convolutional Neural Networks
by Md. Rezaul Karim, Mohit Sewak, Pradeep Pujari | Released June 2018 | ISBN: 9781789535037
Tackle all CNN-related queries with this fast-paced guideAbout This VideoFast-paced guide with use cases and real-world examples to help you master CNN techniquesImplement CNN models on image classification, transfer learning, object detection, instance segmentation, GANs, and moreImplement powerful use-cases such as image captioning, reinforcement learning for hard attention, and recurrent attention modelsIn DetailConvolutional Neural Network (CNN) is revolutionizing several application domains such as visual recognition systems, self-driving cars, medical discoveries, innovative e-commerce, and more. You will learn to create innovative solutions around image and video analytics to solve complex machine learning- and computer vision-related problems and implement real-life CNN models. This course starts with an overview of deep neural networks using image classification as an example and walks you through building your first CNN: a human face detector. You will learn to use concepts such as transfer learning with CNN and auto-encoders to build very powerful models, even when little-supervised training data for labeled images is available. Later we build upon this to build advanced vision-related algorithms for object detection, instance segmentation, image captioning, attention mechanisms for vision, and recurrent models for vision. By the end of this course, you should be ready to implement advanced, effective, and efficient CNN models professionally or personally, by working on a complex image and video datasets.All the code and supporting files for this course are available on Github at https://github.com/PacktPublishing/Practical-Convolutional-Neural-Networks-Video- Show and hide more
- Chapter 1 : Deep Neural Networks – Overview
- The Course Overview 00:05:10
- Building Blocks of a Neural Network 00:02:02
- Handwritten Number Recognition with Keras and MNIST 00:03:32
- Understanding Backpropagation 00:02:57
- Chapter 2 : Introduction to Convolutional Neural Networks
- Convolutional Neural Networks 00:09:37
- Practical Example – Image Classification 00:03:48
- Chapter 3 : Build Your First CNN and Performance Optimization
- Convolution and Pooling Operations in TensorFlow 00:06:17
- Training a CNN 00:04:46
- Building, Training, and Evaluating Our First CNN 00:13:29
- Model Performance Optimization 00:07:19
- Popular CNN Model Architectures 00:04:19
- Chapter 4 : Transfer Learning
- Feature Extraction Approach 00:04:56
- Transfer Learning Example 00:04:21
- Chapter 5 : Autoencoders for CNN
- Introduction to Autoencoders 00:01:22
- Convolutional Autoencoder 00:01:04
- Applications 00:01:08
- Chapter 6 : Object Detection and Instance Segmentation with CNN
- Differences Between Object Detection and Image Classification 00:03:49
- Traditional, nonCNN Approaches to Object Detection 00:04:09
- R-CNN – Regions with CNN Features 00:03:03
- Fast R-CNN – Fast Region-Based CNN 00:02:27
- Faster R-CNN – Faster Region Proposal Network-Based CNN 00:02:46
- Mask R-CNN – Instance Segmentation with CNN 00:03:59
- GAN – Generating New Images with CNN 00:08:52
- Chapter 7 : Attention Mechanism for CNN and Visual Models
- Attention Mechanism for Image Captioning 00:02:31
- Using Attention to Improve Visual Models 00:04:55
Show and hide more