New system enables pattern-recognition systems to convey what they learn to humans.
Computers are good at identifying patterns in huge data sets. Humans, by contrast, are good at inferring patterns from just a few examples.
In a paper appearing at the Neural Information Processing Society’s conference next week, MIT researchers present a new system that bridges these two ways of processing information, so that humans and computers can collaborate to make better decisions.
The system learns to make judgments by crunching data but distills what it learns into simple examples. In experiments, human subjects using the system were more than 20 percent better at classification tasks than those using a similar system based on existing algorithms.
“In this work, we were looking at whether we could augment a machine-learning technique so that it supported people in performing recognition-primed decision-making,” says Julie Shah, an assistant professor of aeronautics and astronautics at MIT and a co-author on the new paper. “That’s the type of decision-making people do when they make tactical decisions — like in fire crews or field operations. When they’re presented with a new scenario, they don’t do search the way machines do. They try to match their current scenario with examples from their previous experience, and then they think, ‘OK, that worked in a previous scenario,’ and they adapt it to the new scenario.”
In particular, Shah and her colleagues — her student Been Kim, whose PhD thesis is the basis of the new paper, and Cynthia Rudin, an associate professor of statistics at the MIT Sloan School of Management — were trying to augment a type of machine learning known as “unsupervised.”
In supervised machine learning, a computer is fed a slew of training data that’s been labeled by humans and tries to find correlations — say, those visual features that occur most frequently in images labeled “car.” In unsupervised machine learning, on the other hand, the computer simply looks for commonalities in unstructured data. The result is a set of data clusters whose members are in some way related, but it may not be obvious how.
The most common example of unsupervised machine learning is what’s known as topic modeling, in which a system clusters documents together according to their most characteristic words. Since the data is unlabeled, the system can’t actually deduce the topics of the documents. But a human reviewing its output would conclude that, for instance, the documents typified by the words “jurisprudence” and “appellate” are legal documents, while those typified by “tonality” and “harmony” are music-theory papers.
The MIT researchers made two major modifications to the type of algorithm commonly used in unsupervised learning. The first is that the clustering was based not only on data items’ shared features, but also on their similarity to some representative example, which the researchers dubbed a “prototype.”
The other is that rather than simply ranking shared features according to importance, the way a topic-modeling algorithm might, the new algorithm tries to winnow the list of features down to a representative set, which the researchers dubbed a “subspace.” To that end, the algorithm imposes a penalty on subspaces that grow too large. So when it’s creating its data clusters, it has to balance three sometimes-competing objectives: similarity to prototype, subspace size, and clear demarcations between clusters.
“You have to pick a good prototype to describe a good subspace,” Kim explains. “At the same time, you have to pick the right subspace such that the prototype makes sense. So you’re doing it all simultaneously.”
The researchers’ first step was to test their new algorithm on a few classic machine-learning tasks, to make sure that the added constraints didn’t impair its performance. They found that on most tasks, it performed as well as its precursor, and on a few, it actually performed better. Shah believes that that could be because the prototype constraint prevents the algorithm from assembling feature lists that contain internal contradictions.
Suppose, for instance, that an unsupervised-learning algorithm was trying to characterize voters in a population. A plurality of the voters might be registered as Democrats, but a plurality of Republicans may have voted in the last primary. The conventional algorithm might then describe the typical voter as a registered Democrat who voted in the last Republican primary. The prototype constraint makes that kind of result very unlikely, since no single voter would match its characterization.
Next, the researchers conducted a set of experiments to determine whether prototype-based machine learning could actually improve human decision-making. Kim culled a set of recipes from an online database in which they had already been assigned categories — such as chili, pasta, and brownies — and distilled them to just their ingredient lists. Then she fed the lists to both a conventional topic-modeling algorithm and the new, prototype-constrained algorithm.
The Latest on: Computers that teach by example
via Google News
The Latest on: Computers that teach by example
- Teaching machines to find critical facilities for emergency responseon July 8, 2021 at 12:53 pm
A natural gas pipeline, for example, might supply fuel to residential customers ... Now, researchers at Idaho National Laboratory are using machine learning to teach computers to recognize critical ...
- Burger joint expense fraud menu unmasked by AIon July 7, 2021 at 7:09 am
Toronto fast food company Good Fortune Burger recently renamed menu items to expense articles as a humorous ploy to disguise items for remote workers, titled “#RECEATS: Renamed menu items so you can ...
- DeVane Medals recognize stellar teaching and scholarshipon July 1, 2021 at 9:32 am
Four Yale professors whose teaching and mentorship have inspired generations of students were recently honored by the university's chapter of Phi Beta Kappa.
- What the “beer game” can teach about supply chain challengeson June 29, 2021 at 8:16 pm
Global supply chains are experiencing whiplash because of an economic phenomenon known as the “bullwhip effect.” ...
- Teaching Startup: How new ventures create their own marketson June 29, 2021 at 3:33 am
One of the biggest mistakes entrepreneurs make is trying to be a competitor in an existing market instead of creating their own market. In this post, I'll give you some case studies and strategie ...
- Harvard’s new Science and Engineering Complex is an example of ‘healthy’ designon June 28, 2021 at 12:30 pm
The architects were told to create the healthiest building in the Harvard University family and the result is a stunning, multi-level display of sustainability.
- 5 ways to prepare and teach online classeson June 28, 2021 at 7:02 am
Online tutoring is becoming more accepted for people every day. With the coronavirus pandemic still affecting the world, there’s never been a better time to work remotely.
- ADU’s College Of Engineering Offers Free Computer-aided Drawing Course To High School Students In Al Ainon June 28, 2021 at 2:59 am
The Al Ain Campus of Abu Dhabi University (ADU) recently concluded a free three-week Computer-Aided Drawing course for high school students. The course ...
- Many Teachers Still Don't Use Computers for Teachingon June 22, 2021 at 12:49 pm
Many teachers worldwide still do not use computers for teaching, and governments should provide them with computers and training to enable students to enjoy a better future.
- Computer Science for All?on June 22, 2021 at 3:44 am
Reitz-Larsen is teaching computer science through movement. The former German-language and business instructor found that linking difficult concepts such as algorithms and the binary system to ...
via Bing News