Saikat Chatterjee: On ability and inability artificial intelligence
Tid: Må 2020-03-30 kl 15.15 - 16.15
Föreläsare: Saikat Chatterjee, KTH
Plats: KTH, F11
In this seminar I will raise questions on ability and inability of deep neural networks in the general perspective of intelligence. What do we expect from an intelligent system? Can we think Artificial Intelligence is really intelligent? How do we define it? For example, if an intelligent system learns with hard examples, what the system should be expected to do for simple examples? We will check with simple computer vision tasks that may be very useful for an autonomous car driving application context as a computer vision problem. Then, I will show examples where neural networks can generate real images that do not exist in reality. Like an artist. Naturally this question continues: is it intelligent and able to do wonders? We will see that it is hard to decide and take a clear side on this ability-inability issue.