Machine learning systems are everywhere. Computer software in these machines predicts the weather, forecasts earthquakes, provides recommendations based on the books and movies we like and, even, applies the brakes on our cars when we are not paying attention.
To do this, computer systems are programmed to find predictive relationships calculated from the massive amounts of data we supply to them. Machine learning systems use advanced algorithms — a set of rules for solving math problems — to identify these predictive relationships using “training data.” This data is then used to construct the models and features within a system that enables it to correctly predict your desire to read the latest best-seller, or the likelihood of rain next week.
This intricate learning process means that a piece of raw data often goes through a series of computations in a given system. The data, computations and information derived by the system from that data together form a complex propagation network called the data’s “lineage.” The term was coined by researchers Yinzhi Cao of Lehigh University and Junfeng Yang of Columbia University who are pioneering a novel approach toward making such learning systems forget.
Considering how important this concept is to increasing security and protecting privacy, Cao and Yang believe that easy adoption of forgetting systems will be increasingly in demand. The pair has developed a way to do it faster and more effectively than what is currently available.
Their concept, called “machine unlearning,” is so promising that the duo have been awarded a four-year, $1.2 million National Science Foundation grant — split between Lehigh and Columbia — to develop the approach.
“Effective forgetting systems must be able to let users specify the data to forget with different levels of granularity,” said Yinzhi Cao, Assistant Professor of Computer Science and Engineering at Lehigh University’s P.C. Rossin College of Engineering & Applied Science and a Principal Investigator on the project. “These systems must remove the data and undo its effects so that all future operations run as if the data never existed.”
There are a number of reasons why an individual user or service provider might want a system to forget data and its complete lineage. Privacy is one.
Naturally, users unhappy with these newfound risks want their data and its influence on the models and statistics to be completely forgotten.
Security is another reason.
The Latest on: Machine unlearning
via Google News
The Latest on: Machine unlearning
- Meet the two UAE residents on a mission to stop Period Poverty across the worldon November 27, 2020 at 1:17 am
Growing up for many women in this region and world over, menstruation or periods were words that were spoken in whispers. The social stigma around women’s monthly biological process was such that many ...
- What to Know About a Negative Body Image and How to Overcome Iton November 25, 2020 at 3:24 pm
Creating a healthier body image involves unlearning what you’ve been taught from media sources. Learning to recognize harmful media messages — whether they’re being sold by advertisers or ...
- Personal trainer's instinctive method draws on old wisdom for modern fitnesson November 18, 2020 at 8:14 am
Personal trainer Mohammad Aboubakr spent years working in remote locations. It taught him lessons that he's now teaching to his Nelson clients.
- “The Human Connect Can Never Be Replaced By Technology”on November 3, 2020 at 12:02 am
We will need adapt to changes swiftly and efficiently while also becoming more flexible, proactive and open to unlearning and ... and innovate in ways which the machines cannot do.
- Confessions of a Debt Collectoron November 1, 2020 at 4:00 pm
Or rather, unlearning a lot. Everything I know about ... Most are answered by machines or by people who say we've got a wrong number. Debtors are cagey about picking up, so we're taught to mask ...
- Lakshmi Machine Consolidated September 2020 Net Sales at Rs 396.34 crore, down 3.18% Y-o-Yon October 29, 2020 at 3:33 am
- Per. of shares (as a % of the total sh. of prom. and promoter group)----- ...
- On Taylor Swift’s “Cardigan” and the Importance of Sentimental Value to Clothingon October 21, 2020 at 7:07 am
Capitalism has taken the human concept of dress by the throat, swallowed it whole, and spit out the corporate fashion industry, an exploitative global machine ... for me, unlearning my obsession ...
- Addressing Western Design Bias in Medtechon October 14, 2020 at 5:00 pm
Emerging markets are the medtech industry’s best prospects for growth, but most medical devices are still designed by engineers based in the United States and Europe. Here's why that needs to ...
- SIT - Adapt To Disruptionon August 29, 2019 at 6:37 pm
By 2022, some 75 million jobs may be displaced by a shift in the division of labour between humans and machines ... proactive approaches to learning, unlearning and relearning, from classrooms ...
via Bing News