News for hackers. Stuff that matters.
Re:What is the difference between deep learning and usual ma... by Kip9000 on Sunday June 05, 2016 @12:22PM (#11841660)
>All of this work (some of these papers have on the order of ten thousands of citations) is now obsolete because you can start with a random initialization of the weights of a neural network and iteratively improve the weights using backprop for any kind of task

Hardly correct. You can't magically learn any kind of task. You can't add arbitrary number of layers and hope for the back prop to do its magic. It is difficult. Deep learning techniques are what makes it somewhat feasible.

SIFT is not obsolete because of NNs. They all have their pros and cons. You have to select the right tool for the job. BTW SIFT is not an edge detector (That's the Canny Transform). It describes images using salient features in scale invariant manner.

Re:What is the difference between deep learning and usual ma... by hacker42 on Sunday June 05, 2016 @01:12PM (#11841922)
Typos fixed. "All" was hyperbole of course, but I think it definitely does not look good for the majority of the work done on features. SIFT was recently outperformed PN-Net for example.
Re:What is the difference between deep learning and usual ma... by nightski on Monday June 06, 2016 @01:55AM (#11844918)
SIFT is also quite old. It's amazing a single technique has retained so much value. Isn't it curious that modern convnets use convolution. On top that, they do convolutions at multiple scales (pooling). Starting to sound very familiar...
Re:What is the difference between deep learning and usual ma... by hacker42 on Monday June 06, 2016 @04:58AM (#11845436)
Actually the neural net approaches are older than SIFT.

Neural nets learn the distribution and even causal factors in the data. To me it seems that this distribution is often just too complex for it to be robustly captured by something that doesn't learn. Learning causal factors critically depends on learning along the depth of the network of latent variables which is a particularly opaque process, but this is what MLPs seem to do quite canonically (convnet being just a restricted special case of MLPs). I mean discerning causal factors is pretty much canonically the act of accumulating evidence with priors (weighted summation), deciding whether it is sufficient evidence and signaling how much it is (non-linearity).

Re:What is the difference between deep learning and usual ma... by nightski on Monday June 06, 2016 @11:50AM (#11847648)
Some of the approaches are, some aren't. SIFT itself builds upon knowledge that is much older than it. Either way it doesn't matter. The OP was arguing that the many years of man effort put into SIFT was a complete waste. I am saying that this is very shortsighted, as non-machine learning vision techniques have heavily influenced how we approach and think about vision problems even when using ML.
Re:What is the difference between deep learning and usual ma... by YeGoblynQueenne on Monday June 06, 2016 @06:40PM (#11851061)
>> SIFT is not obsolete because of NNs. They all have their pros and cons.

Case in point- DNNs for image recogn. use Sobel edge detectors and other "obsolete" filters to do their magickal magic.