News for hackers. Stuff that matters.

jddjdbdbd3

Re:Where Do the Failed 0.1% Go? (2015) [pdf] on Saturday December 10, 2016 @05:42PM (#13148340)
Yeah, took me until early 20s to realise this. I just always thought everyone else had the same contempt for seeking praise from authority that I did. I just thought they were all just really good actors. It simply did not occur to me that anyone would want to recieve praise from a "superior", let alone be annoyed with those who waste the opportunity to gather that praise.
Re:Where Do the Failed 0.1% Go? (2015) [pdf] on Saturday December 10, 2016 @05:35PM (#13148312)
I chose path b. Never did homework. I always forgot it. If you passively deflect enough, people will eventually just give up. Especially when you get good to excellent grades in the exams. The same worked at university. Dont go to lectures, dont do coursework or go to practicals. Get the past exam papers and learn to solve them over a month to two months before the exams. Solid 2.1, job done. Except I was utterly miserible through out that whole time. Lol. I could have been working in theoretical physics had my childhood not been a car wreck. Nope, doing web development, so dull :(
Re:Image Compression with Neural Networks on Thursday September 29, 2016 @03:43PM (#12608201)
Yes you would. But if this becomes widely used you would expect the decode portion to distributed to work on a variety of platforms. Just like jpeg is today. Although I dont think this going to happen. If they can do the same for video, leveraging temporal correlations, then I can see it taking off. In this case the decode neural network would be embedded in the codec.
Re:Computer Vision Research: The deep “depression” on Thursday June 09, 2016 @08:19AM (#11868859)
But this is what the human brain is doing. A large complex statistical analysis of video that provided accurate predictions would contain an understanding of physics, just as our brain does. What you are essentially doing with this is creating a new researcher out of thin air, asking him to work out how to understand video and then when he/she/it succeeds not bothering to ask him how it was done. Then tossing the knowledge in his head away because you didn't come up with it.
Re:Deep Reinforcement Learning: Pong from Pixels on Wednesday June 01, 2016 @03:58AM (#11812757)
Oooh liquid state machines/reservoir computing, what delicious voodoo. Look up optical reservoir computing, what wonderful nonsense. Smash the thing into a million random pieces and look out for the pieces that happen to make your problem easy. Wht. But it works.