GS-3 (Mains), Mains-2018 (English)

Deep Learning – A Subfield of Machine Learning


What is Deep Learning Neural Network?

Deep Learning Neural Network is a machine learning technique that teaches computers to do what comes naturally to humans: learn by example.

In deep learning, a computer model learns to perform classification tasks directly from images, text, or sound. Deep learning models can achieve state-of-the-art accuracy, sometimes exceeding human-level performance.

Deep learning neural network consists:

  • Neural networks, a biologically-inspired programming paradigm which enables a computer to learn from observational data.
  • Deep learning, a powerful set of techniques for learning in neural networks.

Recently, Two new exoplanets (Kepler-90i & Kepler-80g) have been discovered using a deep learning neural networkan artificial intelligence tool that mimics the workings of a human brain.


Applications of deep learning neural network:

-> Deep learning is a key technology behind driverless cars, enabling them to recognize a stop sign, or to distinguish a pedestrian from a lamppost.

-> It is the key to voice control in consumer devices like phones, tablets, TVs, and hands-free speakers.

-> Robotics and Internet of Things (IoT) are the areas that can significantly improve our interaction with outer world.

-> Automatic Game Playing –  A recent example is AlphaGo which beat the world champion.

-> Weather forecasting where training parameters could be wind pattern, air-pressure, temperature and previous weather records of the year etc. so that it could predict weather phenomena without human intervention.

-> Automatic machine translation, deciphering complicated scripts and language modeling.

-> Examination of huge amount of space data to come out with patterns and new discoveries.

-> Restoration of old paintings, identification through low resolution images, automatic music composing etc.


Machine Learning vs Deep Learning:

-> Deep learning is a specialized form of machine learning. A machine learning workflow starts with relevant features being manually extracted from images. The features are then used to create a model that categorizes the objects in the image.

-> With a deep learning workflow, relevant features are automatically extracted from images. In addition, deep learning performs “end-to-end learning” – where a network is given raw data and a task to perform, such as classification, and it learns how to do this automatically.

-> Deep learning algorithms scale with data, whereas shallow learning converges. Shallow learning refers to machine learning methods that plateau at a certain level of performance when you add more examples and training data to the network.

-> A key advantage of deep learning networks is that they often continue to improve as the size of your data increases.



Since the deep learning neural networks are essentially ‘thinking’ entities, care should be taken to employ them with caution. As human brains are capable of self-training and possibly executing nefarious activities, so is the possibility with neural networks of the future.

Also for a developing country like India, where a sizeable proportion of youth is craving for employment, excessive automation might just take away their bread. So governmental vigil is a necessity to regulate their application on a large scale.



Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Google photo

You are commenting using your Google account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s