Convolution Neural Network with Data Augmentation

In this course, you will learn about Convolution Neural Network, Various CNN Architectures, Object Detection and HoG

Neural Networks is the general term that is used for brain like connections. Convolutional Neural Network are the Networks that are specially designed for reading pixel values from Images and learn from it. CNN are the subset of Neural Networks. just like all types of water are liquid but not every liquid is water.

What you’ll learn

  • CNN.

Course Content

  • Introduction –> 3 lectures • 18min.
  • Kernel, Depth, Stride, Padding and Pooling Layer –> 2 lectures • 27min.
  • Relationship between Input Layer and Output Layer –> 3 lectures • 6min.
  • CNN Architectures –> 1 lecture • 3min.
  • Dropout Layer –> 1 lecture • 7min.
  • Practical Exercise –> 2 lectures • 14min.
  • Training CNN –> 5 lectures • 7min.
  • Designing CNN –> 1 lecture • 3min.
  • Data Augmentation –> 4 lectures • 7min.
  • Popular CNN Architectures –> 4 lectures • 32min.
  • Object Detection –> 3 lectures • 10min.
  • Practical Exercises –> 1 lecture • 8min.

Convolution Neural Network with Data Augmentation

Requirements

  • Knowledge of Basic Python.

Neural Networks is the general term that is used for brain like connections. Convolutional Neural Network are the Networks that are specially designed for reading pixel values from Images and learn from it. CNN are the subset of Neural Networks. just like all types of water are liquid but not every liquid is water.

 

CNN is a supervised type of Deep learning, most preferable used in image recognition and computer vision

 

This course is explained in very simple English Language with examples. You will learn all the concepts of CNN in detail and their usage. There are 3 practical examples provided.

 

In this course, we will cover following topics:

1 CNN History: When it started and why there is separate structure for CNN. Why there was need for CNN.

2 CNN Architectures: Various architectures of CNN are discussed like, GoogleNet, Lexnet, Inception, etc. And, the difference between the various models among themselves.

3 Object Detection: Applications of Object Detection, Algorithms of Object Detection and Types and Speed of various ODs

4 HOG

5 Data Augmentation

6 Pooling Layer, Drop Out Layer, Flatten, Conv2D Layers and Epocs

7 Stride and Padding

8 Activation Functions: Sigmoid, ReLu and Softmax Activation Functions

9 Fully Connected Layers

10 Practical Examples

 

Apart from this, you will also learn about Keras Implementation and Layers in CNN

 

 

Get Tutorial