After understanding machine-learning concepts, we can now shift our focus to deep learning concepts. Deep learning is a division of machine learning and is considered a vital step taken by researchers in recent decades. Examples of deep learning implementation include applications like image recognition and speech recognition. TensorFlow Course has been prepared for python developers who focus on research and development with various machine learning and deep learning algorithms. 

Following are the 2 important types of deep neural networks − 

Convolutional Neural Networks 

Recurrent Neural Networks 

In this chapter, we will focus on CNN, Convolutional Neural Networks. 

Convolutional Neural networks are designed to process data through multiple layers of arrays. This type of neural network is used in applications like image recognition or face recognition. The primary difference between CNN and the other ordinary neural network is that CNN takes input as a two-dimensional array and operates directly on the pictures rather than focusing on feature extraction which other neural networks concentrate on. 

The dominant approach of CNN includes solutions for problems of recognition. Top companies like Google and Facebook have invested in research and development towards recognition projects to get activities done with greater speed. 

A convolutional neural network uses three basic ideas − 

- Local respective fields 

- Convolution 

- Pooling 

Let us understand these ideas in detail. 

CNN utilizes spatial correlations that exist within the input data. Each concurrent layer of a neural network connects some input neurons. This specific region is named the local receptive field. The local receptive field focuses on the hidden neurons. The hidden neurons process the input data inside the mentioned field not realizing the changes outside the specific boundary. 

Following is a diagram representation of generating local respective fields

If we observe the above representation, each connection learns the weight of the hidden neuron with an associated reference to movement from one layer to another. Here, individual neurons perform a shift from time to time. This process is named “convolution”. 

The mapping of connections from the input layer to the hidden feature map is defined as “shared weights” and the bias included is named “shared bias”. 

CNN or convolutional neural networks use pooling layers, which are the layers, positioned immediately after CNN declaration. It takes the input from the user as a feature map that comes out of convolutional networks and prepares a condensed feature map. Pooling layers help in creating layers with neurons of previous layers. 

For more information on TensorFlow check out this YouTube link: https://www.youtube.com/watch?v=lgEWExC54yU