Making A.I. Systems that See the World as Humans Do
A Northwestern University team developed a new computational model that performs at human levels on a standard intelligence test. This work is an important step toward making artificial intelligence systems that see and understand the world as humans do.
“The model performs in the 75th percentile for American adults, making it better than average,” said Northwestern Engineering’s Ken Forbus. “The problems that are hard for people are also hard for the model, providing additional evidence that its operation is capturing some important properties of human cognition.”
The new computational model is built on CogSketch, an artificial intelligence platform previously developed in Forbus’ laboratory. The platform has the ability to solve visual problems and understand sketches in order to give immediate, interactive feedback. CogSketch also incorporates a computational model of analogy, based on Northwestern psychology professor Dedre Gentner’s structure-mapping theory. (Gentner received the 2016 David E. Rumelhart Prize for her work on this theory.)
Forbus, Walter P. Murphy Professor of Electrical Engineering and Computer Science at Northwestern’s McCormick School of Engineering, developed the model with Andrew Lovett, a former Northwestern postdoctoral researcher in psychology. Their research was published online this month in the journal Psychological Review.
The ability to solve complex visual problems is one of the hallmarks of human intelligence. Developing artificial intelligence systems that have this ability not only provides new evidence for the importance of symbolic representations and analogy in visual reasoning, but it could potentially shrink the gap between computer and human cognition.
While Forbus and Lovett’s system can be used to model general visual problem-solving phenomena, they specifically tested it on Raven’s Progressive Matrices, a nonverbal standardized test that measures abstract reasoning. All of the test’s problems consist of a matrix with one image missing. The test taker is given six to eight choices with which to best complete the matrix. Forbus and Lovett’s computational model performed better than the average American.
“The Raven’s test is the best existing predictor of what psychologists call ‘fluid intelligence, or the general ability to think abstractly, reason, identify patterns, solve problems, and discern relationships,’” said Lovett, now a researcher at the US Naval Research Laboratory. “Our results suggest that the ability to flexibly use relational representations, comparing and reinterpreting them, is important for fluid intelligence.”
The ability to use and understand sophisticated relational representations is a key to higher-order cognition. Relational representations connect entities and ideas such as “the clock is above the door” or “pressure differences cause water to flow.” These types of comparisons are crucial for making and understanding analogies, which humans use to solve problems, weigh moral dilemmas, and describe the world around them.
“Most artificial intelligence research today concerning vision focuses on recognition, or labeling what is in a scene rather than reasoning about it,” Forbus said. “But recognition is only useful if it supports subsequent reasoning. Our research provides an important step toward understanding visual reasoning more broadly.”
Receive an email update when we add a new ARTIFICIAL INTELLIGENCE article.
The Latest on: Artificial intelligence
via Google News
The Latest on: Artificial intelligence
With The Great Power Of Artificial Intelligence Comes Great Responsibility
on May 25, 2019 at 7:52 am
Artificial intelligence (AI) has been mainly the passion of data science labs and development shops. Lately, however, the implications of its potential impact on business -- in the form of enhanced ... […]
Artificial intelligence, cybersecurity talent top list of hard-to-find skills
on May 25, 2019 at 6:56 am
Application development workloads keep growing, but developer teams are not. If anything, development skills are increasingly in precious short supply. That's the word from the latest survey of 3,300 ... […]
Artificial Intelligence Won’t Save Facebook From Hate Speech
on May 25, 2019 at 6:00 am
So AI isn’t the panacea for a safe and secure Facebook after all. Guy Rosen, vice president of integrity at Facebook, acknowledged during a security update with reporters on Thursday that artificial ... […]
Automotive Artificial Intelligence Market Potential Growth, Challenges and Global Forecast by 2028
on May 25, 2019 at 4:27 am
May 25, 2019 (WiredRelease via COMTEX) -- MarketResearch.Biz recently published a report on the Global Automotive Artificial Intelligence Market 2019, which features genuine and accurate information ... […]
Artificial Intelligence in Big Data Analytics and IoT Markets, 2019 - Global Market will Exceed $24Bn by 2024
on May 24, 2019 at 8:13 am
DUBLIN, May 24, 2019 /PRNewswire/ -- The "Artificial Intelligence in Big Data Analytics and IoT: Market for Data Capture, Information and Decision Support Services 2019-2024" report has been added ... […]
Artificial Intelligence will soon enable tracking of air pollution from every power plant in the world
on May 24, 2019 at 6:17 am
Why it matters: Using technology to solve everyday problems is a noble undertaking, one that's being led by WattTime to help tackle air pollution at a global level. The firm plans to launch a tracking ... […]
Artificial Intelligence in Manufacturing Market size worth $16bn by 2025: Global Market Insights, Inc.
on May 24, 2019 at 5:47 am
The artificial intelligence (AI) in manufacturing market for energy & power sector is predicted to grow at a CAGR of over 41% during the projected time period. The companies are investing in AI ... […]
Artificial Intelligence Could Soon Tell You Whether To Go To A&E Or Not
on May 24, 2019 at 2:58 am
In a bid to relieve pressures on accident and emergency (A&E) units in Birmingham, patients could soon undertake a two-minute triage with artificial intelligence (AI) to check whether their symptoms ... […]
Here's What You Can Expect From Artificial Intelligence At Work
on May 23, 2019 at 1:22 pm
Artificial intelligence is more dangerous than nuclear weapons. That's according to Elon Musk, who warned against the dangers of this technology at South by Southwest in 2018. Not every entrepreneur ... […]
via Bing News