Re:Meta Unveils New AI Supercomputer
by arduinomancer on Monday January 24, 2022 @03:59PM
(#30063952)
Well the theory for the end-to-end image based self-driving models is that they are supposed to cover that.
The reasoning is that given enough training data the system would know the pedestrian is going to jump out or the cyclist is going to fall just based on sheer volume of training examples. It would have seen that scenario tons of times in the image data.
Whether that will actually work is the question though
The reasoning is that given enough training data the system would know the pedestrian is going to jump out or the cyclist is going to fall just based on sheer volume of training examples. It would have seen that scenario tons of times in the image data.
Whether that will actually work is the question though