Practical Convolutional Neural Networks [Video]

Practical Convolutional Neural Networks [Video]
Practical Convolutional Neural Networks [Video]
English | MP4 | AVC 1920×1080 | AAC 48KHz 2ch | 1h 52m | 500 MB

Tackle all CNN-related queries with this fast-paced guide

Convolutional 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.

An easy-to-follow, concise and illustrative guide explaining core ConvNet concepts to help you understand, implement and deploy your CNN models quickly. The course has theoretical content for research and algorithms and the practical parts are implemented in code.

What You Will Learn

  • From CNN basic building blocks to advanced concepts, understand practical areas they can be applied to
  • Build an image classifier CNN model to understand how different components interact with each other, and then learn how to optimize it
  • Learn different algorithms that can be applied to object detection and instance segmentation
  • Learn advanced concepts (such as attention mechanisms for CNN) to improve prediction accuracy
  • Understand transfer learning and implement award-winning CNN architectures such as VGG, ResNet, and more
  • Understand how generative adversarial networks work and how they can create new, unseen images
Table of Contents

The Course Overview
Building Blocks of a Neural Network
Handwritten Number Recognition with Keras and MNIST
Understanding Backpropagation
Convolutional Neural Networks
Practical Example – Image Classification
Convolution and Pooling Operations in TensorFlow
Training a CNN
Building, Training, and Evaluating Our First CNN
Model Performance Optimization
Popular CNN Model Architectures
Feature Extraction Approach
Transfer Learning Example
Introduction to Autoencoders
Convolutional Autoencoder
Differences Between Object Detection and Image Classification
Traditional, nonCNN Approaches to Object Detection
R-CNN – Regions with CNN Features
Fast R-CNN – Fast Region-Based CNN
Faster R-CNN – Faster Region Proposal Network-Based CNN
Mask R-CNN – Instance Segmentation with CNN
GAN – Generating New Images with CNN
Attention Mechanism for Image Captioning
Using Attention to Improve Visual Models