One-shot Learning with Memory-Augmented Neural Networks

Re:One-shot Learning with Memory-Augmented Neural Networks by colllectorof on Friday May 20, 2016 @11:52PM (#11743120)

It doesn't. The claim they're making is that instead of learning labels from bazillion similar example, they use bazillion of diverse examples to train a more generic classifier capable of "learning" correct labels from just a few (i.e. 5) examples.

They compare it with human performance claiming their algorithm is better, but it's kind of a bullshit claim, since people weren't allowed to use scratch paper or see previous examples. So instead of a pattern-matching test they turned this into a memory test. Typical of current AI research. Those people will do anything to be able to claim "better than human" performance.

[ Parent | on HN ]

Re:One-shot Learning with Memory-Augmented Neural Networks by eli_gottlieb on Saturday May 21, 2016 @10:31AM (#11744794)

They also didn't do any comparisons, or even make mention of, the hierarchical Bayesian models that were used to attain human-level performance (by trying to mimic exactly how the human mind does it).

[ Parent | on HN ]

Re:One-shot Learning with Memory-Augmented Neural Networks by alistproducer2 on Saturday May 21, 2016 @03:10PM (#11745763)

Thanks

[ Parent | on HN ]