News for hackers. Stuff that matters.
Re:Failures of Deep Learning by rectangletangle on Friday March 24, 2017 @05:38PM (#13952438)
A lot of useful analogies for N-dimensional space can be abstracted from the simple transition from 2 to 3 dimensions.
Re:Failures of Deep Learning by joeyo on Friday March 24, 2017 @05:59PM (#13952581)
"To deal with a 14-dimensional space, visualize a 3-D space and say 'fourteen' to yourself very loudly." -- Geoff Hinton
Re:Failures of Deep Learning by bitL on Friday March 24, 2017 @07:41PM (#13953144)
A math student and an engineering student went together to a presentation called "14-dimensional space topology". As the presentation progressed, engineering student became more and more frustrated as she could only grasp a few simple initial examples but the deeper the presentation went, the worse was the understanding. Yet the math student was absolutely enthusiastic, often asking the presenter various complicated questions and looking he enjoyed himself a lot. With a massive headache in the end, the engineering student turned to math student and asked: "How could you understand the presentation? I was able to understand 2D, 3D but once we increased number of dimensions I got lost and never understood anything about 14D!" The math student looked at her with a confident careless look and said: "It was simple. I imagined everything in N dimensions, and then just reduced it to 14".
Re:Failures of Deep Learning by wnoise on Friday March 24, 2017 @09:24PM (#13953551)
"and then let N=14" is how I've heard it.