Dr. Constantinos Daskalakis, the Greek MIT professor who solved the puzzle of the Nash Equilibria, said that one of the main concerns of humanity is the credibility of technology.
Speaking in a packed auditorium at the Aristotle University of Thessaloniki last week, the Greek genius mesmerised the audience with his theories on Artificial Intelligence and its importance on the future of mankind.
According to Dr. Daskalakis, today one of the main concerns of humanity is the credibility of technology. Speaking on Artificial Intelligence, he said that, “There are big issues of reliability and one of the reasons is that when the data you feed the algorithm are incomplete or unrepresentative, can lead to faulty or insufficient mental functions. For example, why did a (driver-less) Tesla car smash into a truck stopped in the left lane? Maybe because the data that was entered to train the algorithm did not include the possibility that a car has stalled in the left lane of the highway because this is rarely happening. The algorithm will process the incomplete data we have given it and incorporate this shortage.” He added that MIT students “attacked” the best image recognition algorithm available and made it “think” that a three-dimensional turtle printed on a 3D printer was a shotgun. “We do not have such credible Artificial Intelligence today, we are trying to create ways to protect algorithms from such attacks,” he said.
Another issue that man has to deal with in developing Artificial Intelligence is the moral dilemmas. “A classic problem is this: Think of making self-guided cars driving in city streets. Inevitably, one of them will find itself in a phase of recognizing the fact that in a few seconds an inevitable pedestrian accident will occur. Then the car understands that it faces two possibilities: to go straight and kill the pedestrians or go left, hit the barrier and kill the passengers. The car can not save both, so how will it make the decision? The car also understands that the pedestrians are an 8-year-old boy, his dad, 41, and their dog and the passengers are a 30-year-old pregnant woman and her boyfriend. How do I design the algorithm that will make the decision on who will live?”
According to Dr. Daskalakis, Artificial Intelligence is like a baby. The baby comes into the world with genetic features, but it is mostly tabula rasa. Parents give the child data and goals. If the data that the baby receives contain racist views or prejudices or positions, these positions will be adopted by the child. The same goes for Artificial Intelligence, which learns from its interaction with people.
A good example is a chatbot (a robot that makes a dialogue through text or sound). A group of users attacked it, feeding it racist and conspiratorial content. “Within 17 hours the chatbot became a crazy racist and conspirator,” the professor noted.
There are also issues of impartiality, because, “If the data is incomplete, Artificial Intelligence will adopt statistics that are not representative. And here, for example, the question is: I’m making technology that understands if someone is worthy of a loan, but I have incomplete information about a population group. What then? We have to protect Artificial Intelligence from making such statistical errors, but the problem is that statistics is a tough science,” he noted.
Constantinos Daskalakis is an associate professor of computer science and electrical engineering at MIT. He received his diploma in electrical and computer engineering from the National Technical University of Athens, and a Ph.D. in electrical engineering and computer sciences from University of California-Berkeley.
He has been honored with the 2007 Microsoft Graduate Research Fellowship, the 2008 ACM Doctoral Dissertation Award, the Game Theory and Computer Science Prize from the Game Theory Society, the 2010 Sloan Fellowship in Computer Science, the 2011 SIAM Outstanding Paper Prize, the 2011 Ruth and Joel Spira Award for Distinguished Teaching, the 2012 Microsoft Research Faculty Fellowship, and the 2015 Research and Development Award by the Vatican Giuseppe Sciacca Foundation. He is also a recipient of Best Paper awards at the ACM Conference on Economics and Computation in 2006 and in 2013.