Artificial Intelligence Vs. Machine Learning Vs. Deep Learning [Explained]
Artificial Intelligence (AI) is a computer’s attempt to imitate human intelligence. Where as Machine learning focuses on analyzing large chunks of data and learning from it. On the other hand, Deep learning allows the computer to actually learn and differentiate and make decisions like human.
Artificial Intelligence (AI), Machine learning, Deep learning all three are now the buzzword in the industry. Especially they have impact in the business industry and specifically in the information technology center. To a layman these terms might be confusing.
Some people afraid of that this technological advancement may lead to an end of the world. There is no denying that they do have significant implications in today’s world. It is Artificial Intelligence (AI) that had allowed for the development of self-drive cars, face recognition, web
search, Industrial robots, missile guidance and even tumor detection.
Without Artificial Intelligence (AI) or Machine learning, the world would still be back in the dark ages. It is only due these things that we are moving into a technological advance future.
Artificial Intelligence (AI) is not a new concept. It is has existed since 1960’s. When it was developed in order to develop computers that would be able to do things that humans are capable to do such as “learning” and “solving problems”.
Most popular example of Artificial Intelligence (AI) is a computer playing chess against human player. This shows the computers are able to think and plan ahead.
The current scopes of Artificial Intelligence (AI) include understanding human speech, competing at high levels in strategic games, as well as driving cars and many more.
Why Facebook Shutdown Artificial Intelligence (AI) Robots Project?
Facebook shutdown its Artificial Intelligence (AI) project when their two Robots start Talking to each other in their own language. Facebook abandoned the project after when two robots named as Alice and Bob start chatting with each other in a strange language that only they can understand.
Both the chatbots came to create their own changes to English which make them easier to work – but which remained mysterious to humans that supposedly look after them.
The robots been instructed to work out how to negotiate with each other over a trade and improve their bartering as they went along. But they were not told to use comprehensible English allowing them to create their own “shorthand” according to researchers.
Machine Learning is a subset of Artificial Intelligence (AI). It can attempt to develop machine which can work without programming. In Artificial Intelligence (AI), a machine is programmed to do something. While the machine in this scenario is smart, it does not learn.
The intelligence is programmed into the computer, whereas machine learning allows the computer to learn something new, something that is not programmed to do.
The machine or computers learn via the process of data mining, When new data is fed into the computer, the computer will analyze the data and absorb the information. It can then use the data to detect patterns in data and then adjust programs action accordingly.
An example of this would be its use in Facebook news feed. Here the unsupervised algorithms observe user actions and their pattern to decide which content would be more relevant to users. It then show the user relevant content, which will bee ranked higher on news feed.
Other Example of Machine learning is Identifying tweets on the twitter. Social media hate speech and fake news have become worldwide phenomena in the digital age. While offensive posts are problem, it is even worse when they are inaccurate or wrongly attributed to people through false profiles.
A popular machine learning application of natural language processing (NLP) is sentiment analysis. This allows thousands of text documents to be scanned for certain filters within a second. For example, Twitter can process posts for racists or sexist remark and separate these tweets from others.
Eugene Aiken took a project analyze the posts of two people and determine the probability that a specific tweet came from one particular user . To do this he used the tweets of two well known political rivals : Donald Trump and Hillary Clinton.
This in involved several stages:
1. Scrape their tweets.
2. Run them through a natural language processor.
3. Classify them with a machine learning algorithm.
4. Used the predict-proba method to determine probability.
With the result, Eugene get to identify which tweets were most and least likely of being from Donald trump. This same process can be used to analyze tweets from anyone, include your friends and family.
What is Deep Learning?
Similarly, Deep learning is a subset of Machine learning. In machine learning, the computer is able to recognize patterns, understand speech and makes inferences and predictions. Deep learning takes the ability of computer to learn a step further.
Here the computers are able to actually learn and know things rather than and know things rather than just compare data. Computers are able to learn the characteristics like Face.
Deep learning can also be used to solve the real world problems by tapping into neutral networks that simulate human decision making.
It can be said that basically, Artificial Intelligence (AI) is the computer’s attempt to imitate human intelligence. Whereas Machine learning focuses on analyzing large chunks of data and learning from it. On the other hand, Deep learning allows the computer to actually learn and differentiate and making decisions like humans.
One of the example of Deep learning is: Computer Vision.
Computer vision deals with algorithms and techniques for computers to understand world around using image and video data or in other words. Teaching machines to automate the tasks performed by human visual systems. Common computer visions tasks include image classification, object detection in image and videos, image segmentation and image restoration.
Description in short :
1. The simulation of human intelligence process by machines, especially computer systems.
2. An Umbrella term that encompasses every thing from robotic process automation to actual robotics.
3. Limited scope, Machines are programmed for particular task and they typically can not do anything other than follow programming.
4. Capabilities – Development of self driving cars, face recognition, web search, industrial robots, missile guidance and tumor detection.
5. Examples – IBM’s deep blue, which beat chess and grand master Garry Kasparov at game in 1966.
1. A type of Artificial intelligence (AI) that provides computers with ability to learn without being programmed.
2. Focuses on the development of computer programs that can change when exposed to new data.
3. Large scope, machines can learn to infer and make predictions by analyzing large sets of data.
4. Capabilities – Text-based searches, fraud detection, spam detection, handwriting recognition, image search, etc.
5. Examples – DeepMind’s AlphaGo, which in 2016 beat lee sedol at Go, by analyzing a large data set of expert moves.
1. An aspect of Artificial Intelligence (AI) that is concerned with emulating the learning approach that human beings use to gain certain types of knowledge.
2. A way to automate predictive analytics where the machine learns from a set of data and use it to make predictions.
3. Unlimited scope, machine can learn to emulate human intelligence and decision making by learning and analyzing large sets of data.
4. Capabilities – Computer vision, automatic speech recognition, Natural language processing, audio recognition and bioinformatics.
5. Examples – Automatic Game Playing or Automatic Handwriting Generation
Subscribe to get your daily round-up of top tech stories!