Over the past few years, the terms Deep Learning and Machine Learning have firmly worked its way into business language when the conversation is about Artificial Intelligence (AI), Big Data and Analytics. Just to show you the kind of attention they are getting, here is the Google Trends for these keywords:
Credit: Google Trends (Blue: Deep Learning, Red: Machine Learning)
Let’s start with the basics:
What is Machine Learning?
“Algorithms that parse data, learn from that data, and then apply what they’ve learned to make informed decisions”
Since machine learning deploys an iterative approach to glean from data, machine learning eliminates the need to continuously code or analyze data themselves to solve a solution or present a logic. ML software constitutes of two main elements — statistical analysis and predictive analysis which is used to spot patterns and uncover hidden insights from previous computations without being programmed. This form of AI is only capable of what it is designed for; nothing more, nothing less. For AI designers and the rest of the world, that’s where deep learning holds a bit more promise.
What is Deep Learning?
“Deep Learning is a form of machine learning that is inspired by the structure of the human brain and is particularly effective in feature detection”
While ML focuses on solving real-world problems with neural networks designed to mimic our own decision-making Deep Learning on the other hand focuses even more narrowly on a subset of ML tools and techniques, and applies them to solving just about any problem which requires “thought” – human or artificial.
How does Deep Learning work?
Deep Learning model involves feeding a computer system a lot of data, which it can use to make decisions about other data. This logical structure is similar to how a human would draw conclusions. To achieve this, deep learning uses a layered structure of algorithms called an artificial neural network (ANN). These networks – logical constructions which ask a series of binary true/false questions, or extract a numerical value, of every bit of data which pass through them, and classify it according to the answers received.
Deep Learning can be applied to any form of data – machine signals, audio, video, speech, written words – to produce conclusions that seem as if they have been arrived at by humans – very, very fast ones.
Practical use case of Deep Learning would be a system designed to automatically record and report how many vehicles of a particular make and model passed along a public road. Let’s break it down in below steps:
system would be given access to a huge database of car types, including their shape, size and even engine sound.
Feeding Real World Data:
system would take the data that needs to be processed – real-world data which contains the insights, in this case captured by roadside cameras and microphones.
by comparing the data from its sensors with the data it has “learned”, system can classify, with a certain probability of accuracy, passing vehicles by their make and model.
Comparison of Machine Learning and Deep Learning:
Deep Learning and Machine Learning models differ in their performance as the scale of data increases. When the data is small, deep learning algorithms don’t perform that well, simply because deep learning algorithms need a large amount of data to understand it perfectly. On the other hand, traditional machine learning algorithms with their handcrafted rules prevail in this scenario.
Deep learning algorithms do a large amount of matrix multiplication operations and so, they heavily depend on high-end machines, contrary to traditional machine learning algorithms, which can work on low-end machines.
It is a process of putting domain knowledge into the creation of feature extractors to reduce the complexity of the data and make patterns more visible to learning algorithms to work. Building Machine learning model requires an expert who could identify applied features and hand-code it as per the domain and data type. On the other hand Deep learning algorithms try to learn high-level features from data. This distinctive part of deep learning takes it ahead of traditional machine learning. Therefore, deep learning reduces the task of developing a new feature extractor for every problem. For example, convolutional neural networks will try to learn low-level features such as edges and lines in early layers then parts of faces of people and then the high-level representation of a face.
Solving a problem using traditional machine learning approach requires the problem to be broken down into different parts, solve them individually, and combine them to get the desired result. Contrary to Machine Learning, Deep Learning advocates solving the problem end-to-end.
Because Deep Learning algorithms take into account so many parameters, they usually take long time to get trained. On the other hand, Machine Learning comparatively takes much less time to train, ranging from a few seconds to a few hours.
Machine Learning algorithms give us crisp rules as to why they chose what they chose, so it is particularly easy to interpret the reasoning behind it. But, Deep Learning algorithms fail to interpret the results. Mathematically, one may find out which nodes of a deep neural network were activated to derive the final result but finding out what the neurons were supposed to model and what layers of neurons were doing collectively is not possible.