Convolutional Neural Networks: Fundamentals

Neural Networks    |    Intermediate
  • 12 videos | 45m 19s
  • Includes Assessment
  • Earns a Badge
Rating 3.8 of 6 users Rating 3.8 of 6 users (6)
Learners can explore the concepts of convolutional neural network (CNN); the underlying architecture, principles, and methods needed to build a CNN; and its implementation in a deep neural network. In this 12-video course, you will examine visual perception, and the ability to interpret the surrounding environment by using light in the visible spectrum. First, learn about CNN architecture; how to analyze the essential layers; and the impact of an initial choice of layers. Next, you will learn about nonlinearity in the first layer, and the need for several pooling techniques. Then learn how to implement a convolutional layer and sparse interaction. Examine the hidden layers of CNN, which are convolutional layers, ReLU (rectified linear unit) layers, or activation functions, the pooling layers, the fully connected layer, and the normalization layer. You will examine machine learning semantic segmentation to understand an image at the pixel level, and its implementation using Texton Forest and a random based classifier. Finally, this course examines Gradient Descent and its variants.

WHAT YOU WILL LEARN

  • Illustrate the concept of visual signal perception using a biological example
    Describe convolutional neural network, its architecture, and its layers
    Describe the driving principles of convolutional neural network
    Describe the combined approach of implementing convolutional layer and sparse interaction
    Describe shared parameters and spatial in a convolutional neural network (cnn)
    Describe convolutional padding and strides in a convolutional neural network (cnn)
  • Recognize the relevance and importance of pooling layers in convolutional neural networks (cnns)
    Use relu on convolutional neural networks (cnns)
    Define semantic segmentation and its implementation using texton forest and random-based classifier
    Describe gradient descent and list its prominent variants
    List cnn layers, implementation approaches, layers, and variants of gradient descent

IN THIS COURSE

  • 1m 39s
  • 4m 42s
    After completing this video, you will be able to illustrate the concept of visual signal perception using a biological example. FREE ACCESS
  • Locked
    3.  CNN Architecture
    5m 43s
    Upon completion of this video, you will be able to describe a convolutional neural network, its architecture, and its layers. FREE ACCESS
  • Locked
    4.  Principles of CNN
    4m 10s
    Upon completion of this video, you will be able to describe the driving principles of a convolutional neural network. FREE ACCESS
  • Locked
    5.  Sparse Interaction
    5m 53s
    Upon completion of this video, you will be able to describe the combined approach of implementing a convolutional layer and sparse interaction. FREE ACCESS
  • Locked
    6.  Shared Parameters and Spatial Extents
    3m 49s
    Upon completion of this video, you will be able to describe shared parameters and spatial relationships in a convolutional neural network (CNN). FREE ACCESS
  • Locked
    7.  Convolutional Padding and Strides
    3m 26s
    After completing this video, you will be able to describe convolutional padding and strides in a convolutional neural network (CNN). FREE ACCESS
  • Locked
    8.  Pooling Layers
    5m 10s
    Upon completion of this video, you will be able to recognize the relevance and importance of pooling layers in convolutional neural networks (CNNs). FREE ACCESS
  • Locked
    9.  CNN and ReLU
    2m 8s
    In this video, you will learn how to use ReLU on convolutional neural networks (CNNs). FREE ACCESS
  • Locked
    10.  Semantic Segmentation
    3m 16s
    In this video, you will learn how to define semantic segmentation and its implementation using Texton Forest and a random-based classifier. FREE ACCESS
  • Locked
    11.  Gradient Descent and its Variants
    3m 47s
    After completing this video, you will be able to describe gradient descent and list its variants. FREE ACCESS
  • Locked
    12.  Exercise: CNN Architecture and Principles
    1m 37s
    After completing this video, you will be able to list CNN layers, implementation approaches, and variants of gradient descent. FREE ACCESS

EARN A DIGITAL BADGE WHEN YOU COMPLETE THIS COURSE

Skillsoft is providing you the opportunity to earn a digital badge upon successful completion on some of our courses, which can be shared on any social network or business platform.

Digital badges are yours to keep, forever.

YOU MIGHT ALSO LIKE

Course Deep Learning for NLP: Memory-based Networks
Rating 3.8 of 4 users Rating 3.8 of 4 users (4)
Course Convolutional Neural Networks: Implementing & Training
Rating 4.0 of 6 users Rating 4.0 of 6 users (6)
Course Neural Network Mathematics: Exploring the Math behind Gradient Descent
Rating 4.9 of 7 users Rating 4.9 of 7 users (7)

PEOPLE WHO VIEWED THIS ALSO VIEWED THESE

Course Using Apache Spark for AI Development
Rating 4.2 of 20 users Rating 4.2 of 20 users (20)
Course Advanced Reinforcement Learning: Principles
Rating 4.3 of 8 users Rating 4.3 of 8 users (8)
Course Fundamentals of Sequence Model: Artificial Neural Network & Sequence Modeling
Rating 4.2 of 10 users Rating 4.2 of 10 users (10)