Introduction to Neural Network: Build your own Network

Introduction

In recent years, the evolution of technology has increased tremendously, and nowadays, deep learning is widely used in many domains. This has achieved great success in many fields, like computer vision tasks and natural language processing. Though we have traditional machine learning algorithms, deep learning plays an important role in many tasks better than machine learning techniques.

Machine learning, which is a subset of Artificial intelligence, includes deep learning. Deep learning is based on artificial neural networks where there are multiple layers of data are processed through these layers, and high-level features are extracted. In machine learning, this feature extraction happens manually, but in deep learning, feature extraction happens automatically because of the neural networks.

Learning Objectives

1. To understand the importance of deep learning and how it is different from machine learning
2. Understanding neural networks and their architecture
3. How to build our own neural networks
4. How the artificial neural networks work and the importance of activation function in it

This article was published as a part of the Data Science Blogathon.

Table of Contents

Why do We Need Deep Learning?

Before the evolution of deep learning, we had traditional machine learning algorithms which performed quite very well. But still, there is something that machine learning cannot perform well. Machine learning cannot process large unstructured data. It runs well with a large amount of structured data. But it cannot perform complex algorithms, and for the same problem statement, deep learning achieves better performance than traditional machine learning algorithms.

Machine learning algorithms cannot perform complex operations, but deep learning algorithms can handle complex algorithms. Finally, feature extraction takes place automatically with deep learning. Traditional machine learning techniques require domain expertise to identify the applicable features in order to simplify the data and make patterns more apparent to the learning algorithms. The main benefit of deep learning algorithms is that they attempt to learn high-level features from data incrementally. This does away with the necessity for hard-core feature extraction and domain expertise.

What is a Neural Network?

The human brain mainly inspires a neural network. It contains artificial neurons similar to biological neurons in the human brain. The human brain mainly inspires it. It teaches computers to process data. In this layered formation, interconnected nodes are called neurons, and data is transmitted through these nodes. The ANN is made up primarily of three layers. These include the input layer, hidden layers in between, and the output layer.

There are two types of neural networks.

1. Shallow neural networks

2. Deep Neural networks.

In shallow neural networks, there is only one hidden layer between the input and output layers. In deep neural networks, there are at least two hidden layers in between.

Source: DiSHA

The simple three-layer multi-layer perception architectures will make up the shallow neural network (MLP). The shallow architecture consists of an input layer, one hidden layer, and an output layer. Through a specially designed input layer, numerical data that demonstrates and reflects network packet data will be accepted. The output layer will divide into corresponding classes.

Deep neural networks, which are more complicated and have more layers, support a significantly greater level of variety. Deep neural networks’ multi-layer structure enables more creative topologies, such as connecting layers from supervised and unsupervised learning methods into one network and varying the number of hidden layers.

Working of Artificial Neural Network

Initially, all the inputs are passed through the input layer, and some random weights are assigned to each input. All the weights are multiplied with their corresponding input values and then added to form a weighted sum. Bias is added to the weighted sum and then it is passed through the activation function. Based on this, all the activated neurons are then passed through the next layer, which lasts until it reaches the output layer. Then the output is predicted.

What is an Activation Function?

In artificial neural networks, the activation function defines how the weighted sum of the input layer is changed from the input layer to the output layer through the hidden layers in between. If the input provided is large enough, the corresponding neuron is fired and passed to the next network layer. The goal of this activation function is to introduce non-linearity in the network.

Types of Activation Function

1. Linear Activation Function
2. Binary step function
3. Non-linear Activation Function

Some examples of activation functions are Sigmoid, ReLU(Rectified Linear Unit), ELU(Exponential Linear Units), Softmax, and Tanh.

Create Your Own Neural Network

Now let’s see how to build a simple neural network. First, import the necessary libraries, and to begin with, we have to initialize the bias, learning rate, and weights.

Then define the perceptron function defining how to update weights if an error occurs. Finally, if you test the network the output will be 0 or 1, determining whether to fire the neuron or not.

Python Code:

Deep Learning Algorithms

Deep learning algorithms are used to process the data through them. This data is processed through all the layers of the network transferring a simplified representation of the last layer of data to the next layer. As it goes through NN layers, deep learning algorithms learn gradually more about the data. Feature extraction and feature aggregation take place here. Low-level feature detection learning takes place at the early layers of the network.

Deep learning algorithms process data across many NN “layers,” each of which sends a condensed version of the data to the following layer. Most machine learning methods perform effectively on datasets with up to some hundred features or columns. Deep learning algorithms are critical for identifying features and can handle a large number of operations for both structured and unstructured data.

Some examples of deep learning algorithms include,

1. Convolutional Neural Networks(CNN): 

A convolutional neural network (CNN or ConvNet) is a DNN architecture that learns directly from data. CNNs are especially useful for detecting patterns in images that can be used to identify objects and categories.

2. Recurrent Neural Networks(RNN):

A recurrent neural network (RNN) is a type of ANN designed to work with time series data or data containing sequences. Ordinary feedforward neural networks are only intended for data points that are unrelated to one another. But if data is dependent, then these types of networks are used.

3. Long Short-Term Memory Networks(LSTMs):

It is a class of recurrent neural networks (RNNs) that can learn long-term dependencies mainly in sequence prediction problems. In traditional RNNs, the repeating module will have a simple structure.

4. Multilayer Perceptron(MLPs):

In simple words, MLP is a fully connected layer. An MLP is a common type of feedforward ANN. It is made up of three layers: the input layer, the output layer, and the hidden layer.

Applications of Neural Network

Health Care: Deep learning is used in biomedical data analysis. Organizations of all sizes, shapes, and specialties are increasingly interested in how artificial intelligence can help improve patient care while lowering costs and increasing efficiencies. Also, it is used in disease recognition based on patterns.

Convolutional neural networks (CNNs), a type of deep learning, are mainly well-suited to analyzing images like MRI results or x-rays. NLP tools are used for dictating documentation and translating speech to text. Deep learning developers are interested in precision medicine and drug discovery.

Autonomous Vehicles: Deep learning algorithms are used in autonomous vehicles for decision-making. Also used in computer vision tasks.

In autonomous vehicles, for detection and classification, DL is used. This primarily includes using camera-based systems to detect and classify objects. The data collected by the vehicle sensors is collected and interpreted by the system. Also, this monitors the driver. Because neural networks can identify patterns, they can be used to monitor the driver in vehicles. Vehicle powertrains generate a time series of data points. This data can be used to improve motor control and battery management using machine learning.

Computer Vision: Computer vision tasks include object detection, image classification, face recognition, image captioning, and so on. Deep learning algorithms play an important role in these tasks.

Image classification with localization entails assigning a class label to an image and using a bounding box to show the location of an object in the image. Style transfer of images is an application of this. Image colorization, image reconstruction, image super-resolution, and image synthesis, like changing a horse to zebra, are all applications of computer vision that use DL.

Source: Tensorflow

Virtual Assistants: Virtual assistants like Alexa, Siri, Google Assistant, and Microsoft Cortana are built using these deep learning algorithms.

Many daily tasks, like adding events to the calendar, setting a reminder, or tracking expenses, are made much easier by AI assistants. Chatbots, AI avatars, voice assistants,  and domain-specific virtual assistants are all types of AI virtual assistants. Voice assistants, like well-known Siri and Google Assistant products, use automatic speech recognition and natural language processing to provide vocal responses to queries. AI avatars are 3D models that look like humans and are used for entertainment or to add a human connection to virtual customer care interactions.

Conclusion

Deep Learning is a new set of tools, algorithms, and incredibly novel approaches to problem-solving. It is about machines becoming conscious and taking over the duties assigned only to humans due to their superior intellectual abilities than machines. Their structure is most fundamentally similar to that of the human brain.

– With feature learning, deep learning algorithms explore and evaluate the unknown structure in the input distribution and find meaningful representations.

– Deep Learning offers a wide range of uses, which has increased its appeal and led to its use in a number of different industries. Many organizations from many fields or industries use it.

Connect with me on LinkedIn.

The media shown in this article is not owned by Analytics Vidhya and is used at the Author’s discretion.