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
Global X Robotics & Artificial Intelligence Thematic ETF: Still Missing That Human Touch
on May 21, 2019 at 12:47 pm
ROBO is a RoboGlobal ETF focused on investing in companies worldwide, involved in robotics and automation. Despite it being the first-launched robotics ETF, it has since fallen behind the larger ... […]
Artificial Intelligence to Reach Human-Level Intelligence by 2040
on May 21, 2019 at 12:39 pm
NEORIS explains in its recently published insights report how the merger of technology and human intelligence will occur in the next few decades, opening the door to the next stage of humanity's ... […]
Artificial Intelligence Must Be Built On Human Diversity
on May 21, 2019 at 11:50 am
One of the most important yet overlooked aspects of artificial intelligence (AI) is that it’s not intended to replace human brain power. In fact, current and future AI is best conceptualized as ... […]
Aflac learns important lessons about artificial intelligence and people
on May 21, 2019 at 11:29 am
There's a big push among companies to adopt artificial intelligence (AI) tools such as chatbots. But in some cases organizations are finding that they still need the human touch in addition to ... […]
Artificial Intelligence in Big Data Analytics and IoT Markets, 2019-2024: Focus on Data Capture, Information and Decision Support Services
on May 21, 2019 at 10:21 am
Dublin, May 21, 2019 (GLOBE NEWSWIRE) -- The "Artificial Intelligence in Big Data Analytics and IoT: Market for Data Capture, Information and Decision Support Services 2019-2024" report has been ... […]
Artificial Intelligence Was As Good Or Better Than Doctors At Detecting Lung Cancer In Promising Study
on May 21, 2019 at 7:46 am
But the test does have pitfalls: It can miss tumors, or mistake benign spots for malignancies and push patients into invasive, risky procedures like lung biopsies or surgery. The New York Times: A ... […]
Artificial Intelligence (AI) Robots Market 2019 Global Trends, Market Share, Industry Size, Growth, Opportunities and Forecast to 2024
on May 21, 2019 at 6:21 am
WiseGuyReports.com adds “Artificial Intelligence (AI) Robots Market 2019 Global Analysis, Growth, Trends and Opportunities Research Report Forecasting to 2024” reports to its database ... […]
Why Artificial Intelligence Is Driving The New Era Of Brand Engagement
on May 21, 2019 at 3:18 am
2019 has already proven to be a tumultuous year for retail. For every revolution, in the form of customer personalization, interactive mirrors and the promise of omnichannel, it seems another retailer ... […]
AI IN BANKING AND PAYMENTS: How artificial intelligence can cut costs, build loyalty, and enhance security across financial services
on May 20, 2019 at 10:04 pm
Artificial intelligence (AI) is one of the most commonly referenced terms by financial institutions (FIs) and payments firms when describing their vision for the future of financial services. AI can ... […]
via Bing News