Over 70 years ago, researchers who have spearheaded research about artificial intelligence introduced a concept that revolutionized the way we think about how our brain works. That concept was neural networks.
In the human brain, networks of billions of connected neurons make sense of sensory data, allowing us to learn from experience. Artificial neural networks can also filter huge amounts of data through connected layers to make predictions and recognize patterns, following rules they taught themselves.
The application of this concept has been really helpful in the advancement of technology over the years. Now, artificial neural networks are used in pattern recognition (which our phones use to recognize our faces, by the way). Neural networks, however, have difficulty in solving symbolic math problems, which…
include the hallmarks of calculus courses, like integrals or ordinary differential equations. The hurdles arise from the nature of mathematics itself, which demands precise solutions. Neural nets instead tend to excel at probability. They learn to recognize patterns — which Spanish translation sounds best, or what your face looks like — and can generate new ones.
This leads us to a question: can AI do symbolic math?
Surprisingly, the answer is yes, as proven late last year by two computer scientists Guillaume Lample and François Charton.
Their method didn’t involve number crunching or numerical approximations. Instead, they played to the strengths of neural nets, reframing the math problems in terms of a problem that’s practically solved: language translation.
“We both majored in math and statistics,” said Charton, who studies applications of AI to mathematics. “Math was our original language.”
Check out Quanta Magazine to know more about this exciting story.
(Image Credit: geralt/ Pixabay)