DATA STRUCTURES AND ALGORITHMS PIC CONVOLUTIONAL NEURAL NETWORK

DATA STRUCTURES AND ALGORITHMS PIC: CONVOLUTIONAL NEURAL NETWORK

INTRODUCTION

Neural network What is a Neural Network? An artificial neural network learning algorithm, or neural network, or just neural net , is a computational learning system that uses a network of functions to understand translate a data input of one form into a desired output, usually in another form. The concept of the artificial neural network was inspired by human biology and the way neurons of the human brain function together to understand inputs from human senses.

Introduction to CNN (convolutional neural network): When it comes to Machine Learning, Artificial Neural Networks perform really well. Artificial Neural Networks are used in various classification task like image, audio, words. Different types of Neural Networks are used for different purposes, for example for predicting the sequence of words we use Recurrent Neural Networks more precisely an LSTM, similarly for image classification we use Convolution Neural Network. In this blog, we are going to build basic building block for CNN.

The term “convolutional” means mathematical function derived by integration from two distinct functions. It includes rolling different elements together into a coherent whole by multiplying them. Convolution describes how the other function influences the shape of one function. In other words, it is all about the relations between elements and their operation as a whole.

DEFINITION

CNN is a specialized kind of neural network for processing data that has a known, grid-like topology, such as time-series (1 D grid) , image data (2 D grid) , etc. CNN is a deep learning algorithm, it is used in various fields like speech recognition, image retrieval and face recognition.

Layers in CNN: i. Input layer ii. Hidden layer iii. Output layer

Input Layers: It’s the layer in which we give input to our model. The number of neurons in this layer is equal to total number of features in our data (number of pixels incase of an image). Hidden Layer: The input from Input layer is then feed into the hidden layer. There can be many hidden layers depending upon our model and data size. Each hidden layers can have different numbers of neurons which are generally greater than the number of features. The output from each layer is computed by matrix multiplication of output of the previous layer with learnable weights of that layer and then by addition of learnable biases followed by activation function which makes the network nonlinear. Output Layer: The output from the hidden layer is then fed into a logistic function like sigmoid or softmax which converts the output of each class into probability score of each class.

Here’s the basic python code for a neural network with random inputs and two hidden layers. activation = lambda x: 1. 0/(1. 0 + np. exp(-x)) # sigmoid function input = np. random. randn(3, 1) hidden_1 = activation(np. dot(W 1, input) + b 1) hidden_2 = activation(np. dot(W 2, hidden_1) + b 2) output = np. dot(W 3, hidden_2) + b 3

LAYERS

Typical CNN has an architecture consists of : 1) Convolution layer 2) Pooling layer 3) Connected layer.

Convolution layer: • Extract the unique features from the input image. • Preservers the spatial relationship between pixels by learning image features using small squares of input data. • Detect small , meaningful features such as edges with kernels. • (i. e. , identifying elements of an object, the face of certain man, etc. ).

Convolution layer Example

Then goes Rectified Linear Unit layer (aka Re. Lu). This layer is an extension of a convolutional layer. The purpose of Re. Lu is to increase the non-linearity of the image. It is the process of stripping an image of excessive fat to provide a better feature extraction.

Pool Layer: • Reduce dimensionality, • In all cases, pooling helps to make the representation become approximately invariant to small translations of input. • Local translation can be very useful property if we care more about whether some feature is present than exactly where it is.

Types of pooling: i. Max (works better) ii. Average iii. Sum

Max pooling

Average pooling

SUM pooling

Connected layer

The connected layer is a standard feed-forward neural network. It is a final straight line before the finish line where all the things are already evident. And it is only a matter of time when the results are confirmed.

STRUCTURE

Applications of CNN

Some of the key applications of CNN are listed here – • Decoding Facial Recognition • Analyzing documents • Historic and environmental collections • Understanding climate • Grey areas • Advertising

Other Interesting Fields CNNs are poised to be the future with their introduction into driverless cars, robots that can mimic human behavior, aides to human genome mapping projects, predicting earthquakes and natural disasters, and maybe even self-diagnoses of medical problems. So, you wouldn't even have to drive down to a clinic or schedule an appointment with a doctor to ensure your sneezing attack or high fever is just the simple flu and not symptoms of some rare disease. One problem that researchers are working on with CNNs is brain cancer detection. The earlier detection of brain cancer can prove to be a big step in saving more lives affected by this illness.

Thank you