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
- A patron saint of the internet? The pope is on iton June 28, 2020 at 4:05 am
A 15-year-old boy who helped spread Roman Catholic teaching online is a good candidate to become patron saint of the internet, the Vatican says.
- Not all can afford online teaching: HCon June 26, 2020 at 5:30 pm
Using this as an example ... in the family and if the teaching is online, then all the three children studying in different standards may not be able to utilize the computer or laptop for such ...
- School year over, worn-out parents analyze what worked, what didn't in at-home lessonson June 26, 2020 at 6:41 am
On a drizzly Monday morning, Jeniffer Trice and four of her children put on raincoats and face masks, stepped outside their home and began the ...
- In a mostly white Illinois town, Brandon Butler took it upon himself to teach Black historyon June 25, 2020 at 4:27 am
ELMWOOD — The computer screen fills with a dozen faces — one Black, the rest white.Welcome to a weekly gathering of "Welcome to ...
- Teaching AI to fourth-graders is a thing nowon June 24, 2020 at 2:00 am
Real-world projects taught by industry leaders help fourth-graders understand AI in an innovative way, an alternative to cranking out a learn-to-code factory.
- UW’s Ward Receives Honor for Excellence in Teachingon June 22, 2020 at 11:18 am
An effective and engaging instructor who has dedicated his career to helping students understand the various aspects of his field is a recipient of a top teaching award at the University of Wyoming.
- Here’s why computer art will never replace human arton June 21, 2020 at 2:07 am
In December 1964, over a single evening session in Englewood Cliffs, New Jersey, John Coltrane and his quartet recorded the entirety of A Love Supreme. This jazz album is considered Coltrane’s ...
- Teaching Machines to Detect Climate Extremeson June 17, 2020 at 6:27 am
Artificial intelligence can be used to analyze massive amounts of data from climate simulations, but more training data are needed.
- What Learning Python Taught Me About Computer Science Education for Young Childrenon June 16, 2020 at 4:27 pm
This past semester, I took an introductory Python course with roughly fifty undergraduate and a handful of graduate peers. The course—“COMP 10: ...
- Helm.ai Pioneers Breakthrough “Deep Teaching” of Neural Networkson June 15, 2020 at 6:39 pm
Helm.ai, a developer of next-generation AI software, today announced a breakthrough in unsupervised learning technology. This new.
via Bing News