Just in:
Nvidia is the dream stock of our lifetime! // Behomes Launches Behomes Hub – Cashback & Networking App for Real Estate Professionals // ICONSIAM Showcases Thai Creativity to the World with “Lost in DOMLAND” — Reinforcing Its Role as a Must-Visit Global Art Destination // “Eternal City” Pompeii Exhibition Opens in Hunan, Marking New Sino-Italian Cultural Exchange // Air Arabia Reinitiates Sharjah–Damascus Flights // BoE charts new wholesale terrain for stablecoins and tokenised assets // OPEC+ Eyes Pause in Production Rises After September Surge // Sharjah Elevates Real‑Estate Platform with New Digital Portal // UAE Hits Milestone with EU Delisting From High‑Risk Financial Watchlist // TÜV SÜD Appoints Interim Leadership Following CEO Transition // Galaxy AI Elevates On‑Device Intelligence with Privacy at Core // Tokyo Real Estate Set for $75 Million Blockchain Shake‑Up // Stonepeak Secures Strategic Co-Control of IFCO Stake // DNA‑Crafted Nanomachines Self‑Assemble in Water // Can India Emerge As The Trusted Leader Of Global South Like Earlier Years? // Ten Tips for a Healthy Summer Garden // Record Global Interest Drives CDB’s Dual‑Currency Bond Triumph // Coffee Chains Join Bitcoin Mania with Bold Treasury Moves // Qingzhen’s Zhanjie Town Leverages Ecological Resources to Drive Industrial Upgrading and Integrate Culture and Tourism for Rural Revitalization // Anhui Unveils Teaser for 2025 World Manufacturing Convention, Extending a Global Invitation to Innovate Together //

Making AI systems that see the world as humans do

1484850298 makingaisyst

An example question from the Raven’s Progressive Matrices standardized test. The test taker should choose answer D because the relationships between it and the other elements in the bottom row are most similar to the relationships between the elements of the top rows. Credit: Ken Forbus

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.”

ADVERTISEMENT

The new computational model is built on CogSketch, an 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 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 .

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 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.”


Explore further:
Structure-mapping engine enables computers to reason and learn like humans, including solving moral dilemmas

More information:
Andrew Lovett et al. Modeling visual problem solving as analogical reasoning., Psychological Review (2017). DOI: 10.1037/rev0000039

Source link


Notice an issue?

Arabian Post strives to deliver the most accurate and reliable information to its readers. If you believe you have identified an error or inconsistency in this article, please don't hesitate to contact our editorial team at editor[at]thearabianpost[dot]com. We are committed to promptly addressing any concerns and ensuring the highest level of journalistic integrity.


ADVERTISEMENT
Just in:
Air Arabia Reinitiates Sharjah–Damascus Flights // Abu Dhabi’s Masdar and Iberdrola Back £5 Billion UK Offshore Wind Venture // Can India Emerge As The Trusted Leader Of Global South Like Earlier Years? // IIT Delhi and TeamLease EdTech Kick‑start AI for Healthcare Executive Programme // Stonepeak Secures Strategic Co-Control of IFCO Stake // UAE Hits Milestone with EU Delisting From High‑Risk Financial Watchlist // Sharjah Elevates Real‑Estate Platform with New Digital Portal // BoE charts new wholesale terrain for stablecoins and tokenised assets // Dong Yuhui’s Fujian Journey: The Sea’s Lesson – 30% Destiny, 70% Determination // Celebratory 911 Club Coupe Marks Half-Century Porsche Partnership // Tokyo Real Estate Set for $75 Million Blockchain Shake‑Up // OPEC+ Eyes Pause in Production Rises After September Surge // Ten Tips for a Healthy Summer Garden // Behomes Launches Behomes Hub – Cashback & Networking App for Real Estate Professionals // Record Global Interest Drives CDB’s Dual‑Currency Bond Triumph // Galaxy AI Elevates On‑Device Intelligence with Privacy at Core // Qingzhen’s Zhanjie Town Leverages Ecological Resources to Drive Industrial Upgrading and Integrate Culture and Tourism for Rural Revitalization // Results of the ixCrypto Index Series Quarterly Review (2025 Q2) & IX Digital Asset Industry Index Series Half Yearly Review (2025 1H) // Anhui Unveils Teaser for 2025 World Manufacturing Convention, Extending a Global Invitation to Innovate Together // Nigeria’s Coastal Highway Passes $747 m Funding Milestone //