Why Does Deep and Cheap Learning Work So Well?
نویسندگان
چکیده
منابع مشابه
Why does deep and cheap learning work so well?
We show how the success of deep learning depends not only on mathematics but also on physics: although well-known mathematical theorems guarantee that neural networks can approximate arbitrary functions well, the class of functions of practical interest can be approximated through “cheap learning” with exponentially fewer parameters than generic ones, because they have simplifying properties tr...
متن کاملComment on "Why does deep and cheap learning work so well?" [arXiv: 1608.08225]
In a recent paper, “Why does deep and cheap learning work so well?”, Lin and Tegmark claim to show that the mapping between deep belief networks and the variational renormalization group derived in [1] is invalid, and present a “counterexample” that claims to show that this mapping does not hold. In this comment, we show that these claims are incorrect and stem from a misunderstanding of the va...
متن کاملWhy Does BitTorrent Work So Well?
BitTorrent (BT) is currently the most popular file-sharing peer-to-peer (P2P) clients [1]. Several reports have shown that it accounts for the majority of peer-to-peer traffic, up to one third of the global Internet traffic. However, leaving the media attention aside for one moment, we ask the question: Why does BT work so well? BT attempts to build robustness to freeloading (i.e. downloading w...
متن کاملWhy does Deep Learning work? - A perspective from Group Theory
Why does Deep Learning work? What representations does it capture? How do higher-order representations emerge? We study these questions from the perspective of group theory, thereby opening a new approach towards a theory of Deep learning. One factor behind the recent resurgence of the subject is a key algorithmic step called pretraining: first search for a good generative model for the input s...
متن کاملPhase retrieval from image intensities: why does exit wave restoration using IWFR work so well?
The iterative wave function reconstruction (IWFR) is one type of in-line holography and retrieves a complex wave function from a set of through-focus images. We have verified that the IWFR provides an extremely good estimate of an atomic-resolution exit wave function (EWF) simply from the Fourier transforms of observed intensities. Thus, the first guess of the EWF using only five images gives a...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Journal of Statistical Physics
سال: 2017
ISSN: 0022-4715,1572-9613
DOI: 10.1007/s10955-017-1836-5