Course details

Convo Nets for Visual Recognition: Computer Vision & CNN Architectures

Convo Nets for Visual Recognition: Computer Vision & CNN Architectures


Overview/Description
Expected Duration
Lesson Objectives
Course Number
Expertise Level



Overview/Description

Learners can explore the machine learning concept and classification of activation functions, the limitations of Tanh and the limitations of Sigmoid, and how these limitations can be resolved using the rectified linear unit, or ReLU, along with the significant benefits afforded by ReLU, in this 10-video course. You will observe how to implement ReLU activation function in convolutional networks using Python. Next, discover the core tasks used in implementing computer vision, and developing CNN models from scratch for object image classification by using Python and Keras. Examine the concept of the fully-connected layer and its role in convolutional networks, and also the CNN training process workflow and essential elements that you need to specify during the CNN training process. The final tutorial in this course involves listing and comparing the various convolutional neural network architectures. In the concluding exercise you will recall the benefits of applying ReLU in CNNs, list the prominent CNN architectures, and implement ReLU function in convolutional networks using Python.



Expected Duration (hours)
0.8

Lesson Objectives

Convo Nets for Visual Recognition: Computer Vision & CNN Architectures

  • discover the key concepts covered in this course
  • define and classify activation functions and provide a comparative analysis with the pros and cons of the different types of activation functions
  • recognize the limitations of Sigmoid and Tanh and describe how they can be resolved using ReLU along with the significant benefits afforded by ReLU when applied in convolutional networks
  • implement rectified linear activation function in convolutional networks using Python
  • list the core tasks that are used in the implementation of computer vision
  • develop convolutional neural network models from the scratch for object photo classification using Python and Keras
  • describe the concept of fully-connected layer and illustrate its role in convolutional networks
  • describe the convolutional neural network training process workflow and the essential elements that we need to specify during the training process
  • list and compare the various architectures of convolutional neural networks
  • recall the benefits of applying ReLU in convolutional neural networks, list the prominent architectures of convolutional neural networks and implement ReLU function in convolutional networks using Python
  • Course Number:
    it_mlacnvdj_02_enus

    Expertise Level
    Intermediate