Info sheet: Introduction to Machine Learning
What is machine learning?
Machine Learning is the science of training computers, to improve their learning over time in autonomous fashion, by feeding them data and information in the form of observations and real-world interactions.
There are different approaches to training computers, such as using basic decision trees, to clustering, to layers of artificial neural networks (see below). The approach depends on the task you’re trying to accomplish and the amount and type of data you have available.
Who uses Machine Learning?
Machine Learning is being applied across many industries including healthcare (personal monitoring of elderly family members), retail (Amazon personalizes your online recommendations), software (Facebook recognizes familiar people in photos) and finance (PayPal evaluates risk and protects against fraud).
When did Machine Learning start?
The origins of Machine Learning began in the 1950s. Today’s computer processing power, ability to capture data and information and lower cost of computers has enabled broader adoption of the technology.
Artificial intelligence and reverse osmosis have been developing for decades. In the 1960s, as work like Sydney Loeb’s delivered membrane technology breakthroughs, the mathematical theory of AI was introduced for inductive inference and prediction. In the 1970s RO innovators honed the spiral wound element, and AI innovators identified backpropagation, a method to train neural networks.
How does Machine Learning work at Synauta?
We use a subset of Machine Learning called Supervised Learning. This is where the computer learns a function that maps an input to an output (based on example input-output pairs). In Supervised Learning, each example is a pair consisting of an input object and a desired output value.
A Supervised Learning algorithm analyzes the training data and produces an inferred function, which can be used for mapping new scenarios. The optimal scenario of Supervised Learning enables the algorithm to correctly determine new outputs for unseen instances.
What is Artifical Intelligence, Machine Learning, Data Science, Digital Twin?
Artificial Intelligence (AI) is a broad umbrella term, commonly thrown about in popular culture. Simply put, it is enabling machines to execute reasoning by replicating human intelligence.
Machine Learning is a subset of AI and uses statistical models.
Data Science is a discipline focused on data modelling and data warehousing to track ever-growing data sets.
A Digital Twin is simply a digital replica of a physical asset. A digital twin requires sensors or scans and acts as a ‘bridge’ between reality and simulation.
Why is Machine Learning becoming a part of business?
Machine Learning makes computer processes more efficient, cost effective and reliable. Ultimately it helps people control systems more efficiently and make data driven decisions, even when there are massive amounts of data.