Course details

Convo Nets for Visual Recognition: Filters & Feature Mapping in CNN

Convo Nets for Visual Recognition: Filters & Feature Mapping in CNN


Overview/Description
Expected Duration
Lesson Objectives
Course Number
Expertise Level



Overview/Description

In this 13-video course, you will explore the capabilities and features of convolutional networks for machine learning that make it a recommended choice for visual recognition implementation. Begin by examining the architecture and the various layers of convolutional networks, including pooling layer, convo layer, normalization layer, and fully connected layer, and defining the concept and types of filters in convolutional networks along with their usage scenarios. Learn about the approach to maximizing filter activation with Keras; define the concept of feature map in convolutional networks and illustrate the approach of visualizing feature maps; and plot the map of the first convo layer for given images, then visualize the feature map output from every block in the visual geometry group (VGG) model. Look at optimization parameters for convolutional networks, and hyperparameters for tuning and optimizing convolutional networks. Learn about applying functions on pooling layer; pooling layer operations; implementing pooling layer with Python, and implementing convo layer with Python. The concluding exercise involves plotting feature maps.



Expected Duration (hours)
1.1

Lesson Objectives

Convo Nets for Visual Recognition: Filters & Feature Mapping in CNN

  • discover the key concepts covered in this course
  • recognize the capability and features of convolutional networks that makes it a recommended choice for visual recognition implementation
  • illustrate the architecture and the various layers of convolutional networks
  • define the concept and types of filters in convolutional networks along with their usage scenarios to depict the impact of filters on feature sets during the training process
  • demonstrate the approach of using Keras to visualize inputs that maximize the activation of filters in different layers of convolutional networks
  • define the concept of feature map in convolutional networks and illustrate the approach of visualizing feature maps
  • plot the feature map of the first convo layer for given images and visualize the feature map output from every block in the VGG model
  • identify the critical parameters that we need to tune to optimize convolutional networks
  • recall the essential hyperparameters that are applied on convolutional networks for optimization and model refinement
  • work with hyperparameters using Keras and TensorFlow to derive optimized convolutional network models
  • recognize the role of pooling layer in convolutional networks along with the various operations and functions that we can apply on the layer
  • demonstrate how to implement convo and pooling layer in Python
  • recall the various layers of convolutional networks, plot the feature map of the first convo layer for a given image and visualize the Feature map output from every block in the VGG model
  • Course Number:
    it_mlacnvdj_01_enus

    Expertise Level
    Intermediate