For someone new to the field of AI, the difference between the terms Artificial Intelligence (AI), Machine Learning (ML), and Deep Learning (DL) might be puzzling. Well, I was in that position a few months back. Let’s get over this confusion cloud and take a step closer to being an AI wizard!
What is Artificial Intelligence?
Artificial Intelligence is a broad field of computer science aimed at automating intellectual tasks normally performed by humans. It is basically getting computers to simulate human behavior (cognitive process) in order to achieve some goal in varying circumstances. These systems don’t necessarily have to be complex. It is a trait of a machine and even a system that follows a set of rules hard-coded by the programmer is considered AI.
“Artificial Intelligence (AI) is the part of computer science concerned with designing intelligent computer systems, that is, systems that exhibit characteristics we associate with intelligence in human behavior – understanding language, learning, reasoning, solving problems, and so on.” – (Barr & Feigenbaum, 1981)
Artificial Intelligence is classified into three main categories: Artificial Narrow Intelligence, Artificial General Intelligence, and Artificial Super Intelligence. (We’ll discuss these fields in detail in future articles).
A very simple example of an AI system is a computer playing chess. The programmer can enter the rules of chess, the system analyzes the opponent’s moves and plays with the of winning the game.
What is Machine Learning?
Machine Learning is one subset of Artificial Intelligence. These are systems that have the ability to learn from experience and are not explicitly coded. We give the machine some datasets (training datasets) as the input and also what answers we expect as output and it figures generates the rules by identifying some pattern within the training data. The main aim here is to get computers to learn without human intervention.
A major advantage of machine learning is that it reduces manual programming and comes up with unique, unexpected solutions that even programmers and domain experts wouldn’t be able to think of!
An example of a machine learning system is Netflix’s recommendation system. It learns from your previous clicks/views and recommends new movies and TV shows accordingly
Various machine learning methods are Supervised Learning, Unsupervised Learning, Semi-supervise Learning, and Reinforcement Learning.
Core Machine Learning algorithms include: Linear regression, Classification, Clustering, Hidden Markov Models, etc
We’ll delve deeper into ML methods and algorithms in future articles.
What is Deep Learning?
Deep learning is a form of machine learning that uses a layered representation of data. The
term “deep” refers to the number of layers in the network—the more layers, the deeper the network. It is also called a multistage information extraction process. This field works best to perform classification tasks directly from images, text, or sound.
Here’s some stuff that I came across in the MathWorks deep learning ebook: A few examples of deep learning at work:
• A self-driving vehicle slows down as it approaches a pedestrian crosswalk.
• An ATM rejects a counterfeit banknote.
• A smartphone app gives an instant translation of a foreign street sign.
Deep learning is especially well-suited to identification and classification applications such as face recognition, text translation, voice recognition, and advanced driver assistance systems, including lane classification and traffic signal identification.
Neural Networks are the core of deep learning. Various types of neural networks are: FeedForward Neural Network, Radial Basis Function Neural Network, Kohonen Self Organizing Neural Network, Recurrent Neural Network, Convolutional Neural Network, Modular Neural Network.
Again We’ll get deeper into each type of network in future articles!
- https://in.mathworks.com/campaigns/offers/deep-learning-with-matlab.confirmation.html elqsid=1599478644676&potential_use=Student&elqCampaignId=10588