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
- Study: Financial incentives did not markedly increase patient placement on peritoneal dialysison March 23, 2020 at 6:54 am
in combination with machine learning and other artificial intelligence techniques, should improve some performance limitations with incorporating CDSS. The approach to managing high-cost complex ...
- The Destruction of the European Jews, by Raul Hilbergon March 20, 2020 at 5:56 am
“As the machine was thrown into high gear ... For two thousand years, as he says, the Jews had been unlearning the habit of resistance, and in the end they could not, without a revolution, recover it.
- Bentley Continental GT V8 S first drive reviewon March 17, 2020 at 5:00 pm
Not any more; my time in the V8 S was spent unlearning what my brain thought ... and while it’s still no drift machine, if you do run wide in a curve it will tighten its line in direct, precise ...
- Creativity is the new currency for small businesses and startups: Five ways to harness it todayon March 16, 2020 at 12:12 am
This is the faculty all humans share, and it’s what distinguishes us from other creatures and machines. Problem solving is looking at challenges and opportunities ... At the core, it is the freedom ...
- I turned my skateboard into an electric one and it was like snowboarding on asphalton March 11, 2020 at 5:02 am
Skateboarders fear change. Enter the Unlimited x Loaded conversion kit: a kit that lets you transform the old board you know and love into an electric one. Though skateboarding has been a hobby and ...
- Love Aaj Kal And The Myth Of Imtiaz Ali’s ‘Strong’ Women Characterson March 2, 2020 at 1:31 am
Thirteen years and many episodes of unlearning stereotypes ago, Geet seemed like the kind of self-validating machine I yearned to be. For many women, Kareena’s unapologetically self-obsessed ...
- AI for developerson February 29, 2020 at 1:51 am
This unlearning/learning challenge exists at all ... and its business processes by integrating trained machine learning (ML) models into production systems, and designing feedback loops such ...
- The case for allowing machines to patent inventionson February 23, 2020 at 4:00 pm
But should that standard change, as machine learning improves to the point ... Following “cumulative cycles of learning and unlearning, a fraction of these nets interconnect into structures ...
- Research Roundup: Science & Technology Versus the 2019 Novel Coronaviruson February 9, 2020 at 12:41 pm
(University of Notre Dame & Florida Institute of Technology) Machine Unlearning: Fighting for the Right to Be Forgotten In a new paper, researchers propose SISA training, a new framework that ...
- Unlearning Instincts, set of 5, 2019on April 27, 2019 at 11:11 pm
In this series of collages, Kotatkova juxtaposes human heads and animal bodies to form creatures reminiscent of mythological aggregates like minotaurs and harpies. These collages are made of ...
via Bing News