D
Dmitry Krotov
Researcher at IBM
Publications - 33
Citations - 990
Dmitry Krotov is an academic researcher from IBM. The author has contributed to research in topics: Computer science & Content-addressable memory. The author has an hindex of 10, co-authored 24 publications receiving 724 citations. Previous affiliations of Dmitry Krotov include Institute for Advanced Study & Princeton University.
Papers
More filters
Journal ArticleDOI
Infrared Sensitivity of Unstable Vacua
TL;DR: In this paper, the authors examined the cases of instabilities caused by the constant electric fields, expanding and contracting universes and the global de Sitter space and discovered that some unstable vacua have long memory.
Journal ArticleDOI
Unsupervised learning by competing hidden units
Dmitry Krotov,John J. Hopfield +1 more
TL;DR: A learning algorithm is designed that utilizes global inhibition in the hidden layer and is capable of learning early feature detectors in a completely unsupervised way, and which is motivated by Hebb’s idea that change of the synapse strength should be local.
Posted Content
Dense Associative Memory for Pattern Recognition
Dmitry Krotov,John J. Hopfield +1 more
TL;DR: In this paper, the authors proposed a duality between associative memory and neural networks commonly used in deep learning, and demonstrated the utility of the dense memories for two test cases: logical gate XOR and the recognition of handwritten digits from the MNIST data set.
Journal ArticleDOI
Morphogenesis at criticality
TL;DR: It is argued that, as expected from the thermodynamic case, genetic regulatory networks should exhibit behaviors near criticality that are independent of most molecular details, and that the different signatures are related in ways predicted by theory.
Proceedings Article
Dense Associative Memory for Pattern Recognition
Dmitry Krotov,John J. Hopfield +1 more
TL;DR: In this article, the authors proposed a duality between associative memory and neural networks commonly used in deep learning, and demonstrated the utility of the dense memories for two test cases: logical gate XOR and the recognition of handwritten digits from the MNIST data set.