INTRODUCTION TO DEEP LEARNING

In this era of technological advancement, 21st century will be at that level that could not be dreamed. Today, people are benefited from Artificial Intelligence at each and every step of life. For example, Google’s AI prediction, Google Map, ride-hailing services like Uber and Lyft, and many more apps are powered by AI.

AI is advancing at a great pace and deep learning is one of the contributors to that.

Broadly speaking, deep learning is a more approachable name for an artificial neural network. The “deep” in deep learning refers to the depth of the network. An artificial neural network can be very shallow. Neural networks are inspired by the structure of the cerebral cortex. At the basic level is the perceptron, the mathematical representation of a biological neuron. Like in the cerebral cortex, there can be several layers of interconnected perceptrons.

Why Deep Learning is Important Now?

Deep-learning was introduced in the 1940s but recently got popular and catches the eyes of many researchers and engineers because of the following reasons:-

• Increasing Data sets

• Advancement in Hardware

• Increasing Model Sizes

• Open Source Community

How Deep Learning Models Works?

The majority of the deep learning methods utilize neural network architectures and that's why deep learning models are widely known as deep neural networks as well. A deep learning process consists of two key phases --- training and inferring. The training phase can be considered as a process of labeling huge amounts of data identifying their matching characteristics. Here, the system compares those characteristics and memorizes them to come up with correct conclusions when it encounters similar data next time. During the inferring phase, the model makes conclusions and labels unexposed data with the help of the knowledge it gained previously. During the training of deep learning models, professionals use large sets of labeled data and neural network architectures that learn features from the data directly without the need for feature extraction done manually. 

Deep learning is a sub-field of machine learning dealing with algorithms inspired by the structure and function of the brain called artificial neural networks. In other words, It mirrors the functioning of our brains. Deep learning algorithms are similar to how the nervous system structured where each neuron connected the other and passing information.

 

Examples of deep learning in real-world scenarios

A huge number of industries are using deep learning to leverage its benefits. Let’s have a look at a couple of them.

·        Electronics: Deep learning is being utilized in automated speech translation. You can think of home assistance devices that respond to your voice and understand your preferences.

·        Automated driving: With the help of deep learning, automotive researchers are now able to detect objects like traffic lights, stop signs, etc automatically. They’re also using it to detect pedestrians that helps lower accidents.

·        Medical research: Deep learning is being used by cancer researchers to detect cancer cells automatically.

REFERENCE

• iNeuron Deep Learning course
• https://en.wikipedia.org/wiki/Deep_learning