Dmitry Krotov
Scholar

Dmitry Krotov

Google Scholar ID: WeD9ll0AAAAJ
MIT-IBM Watson AI Lab & IBM Research
Neural NetworksMachine LearningArtificial Intelligence
Citations & Impact
All-time
Citations
1,956
 
H-index
19
 
i10-index
25
 
Publications
20
 
Co-authors
21
list available
Resume (English only)
Academic Achievements
  • - Developed Dense Associative Memories with John Hopfield, significantly increasing the information storage capacity of Hopfield Networks.
  • - Selected Publications:
  • - Dense Associative Memory for Pattern Recognition (NeurIPS, 2016)
  • - Large Associative Memory Problem in Neurobiology and Machine Learning (ICLR, 2021)
  • - A new frontier for Hopfield networks (Nature Reviews Physics, 2023)
  • - Energy Transformer (NeurIPS, 2023)
  • - Unsupervised Learning by Competing Hidden Units (PNAS, 2019)
  • - Neuron–astrocyte associative memory (PNAS, 2025)
  • - Memorization to Generalization: The Emergence of Diffusion Models from Associative Memory (arXiv preprint, 2025)
  • - Hierarchical associative memory (arXiv preprint, 2021)
Research Experience
  • - Research Staff Member at the MIT-IBM Watson AI Lab & IBM Research
  • - Former member of the Institute for Advanced Study in Princeton
Background
  • A physicist working on neural networks and machine learning, specializing in associative memory models and brain-inspired AI algorithms.
Miscellany
  • No personal interests or hobbies provided.