The Allen Institute of Artificial Intelligence (AI2) announced on Monday that they have created a new computer program that can solve geometry problems. But for those who fear the rise of AI, rest at ease. The computer is only as smart as an average high school student.
Allen Institute, which is funded by Microsoft, has dubbed the system GeoS. When put to the test, it answered 49 percent of questions SAT style questions correctly.
“If these results were extrapolated to the entire Math SAT test, the computer roughly achieved an SAT score of 500 (out of 800), the average test score for 2015,” said the Allen Institute.
While these results may not seem the most exciting, it is a promising start. The GeoS’ challenge is to make sense of the data it’s being fed and act appropriately- rather than just interpret patterns like many other AI programs.
“Unlike the Turing Test, standardized tests such as the SAT provide us today with a way to measure machines ability to reason and to compare its abilities with that of a human,” said Oren Etzioni, CEO of AI2. “Much of what we understand from text and graphics is not explicitly stated, and requires far more knowledge than we appreciate. Creating a system to successfully take these tests is challenging, and we are proud to achieve these unprecedented results.”
The GeoS analyzes the diagrams and text then applies the geometric information it has been taught to try and solve the problem. In short, the GeoS is trying to understand the diagram.
“We’re excited about GeoS performance on real-world tasks,” said Ali Farhadi, a senior research manager at AI2. “Our biggest challenge was converting the question to a computer-understandable language. One needs to go beyond standard pattern matching approaches for problems like solving geometry questions that require in-depth understating of text, diagram and reasoning.”
Currently, GeoS is able to answer geometry questions about planes. The scientists at the Allen Institute hope to improve the computer so that it can solve the entire SAT Math section. They hope to complete the project within the next three years.
Leave a Reply