Dataset Distillation using Random Feature Approximation

Invention type: Technology / Case number: #24329
License tlo.mit.edu/contact-us

Researchers

Daniela Rus / Alexander Amini / Ramin Hasani / Noel Loo

Departments: Dept of Electrical Engineering & Computer Science, Computer Science & Artificial Intelligence Lab, Electrical Eng & Computer Sci
Technology Areas: Artificial Intelligence (AI) and Machine Learning (ML)
Impact Areas: Connected World

  • systems and methods for efficient dataset distillation using non-deterministic feature approximation
    United States of America | Pending
  • systems and methods for efficient dataset distillation using non-deterministic feature approximation
    Patent Cooperation Treaty | Pending

License this technology

Interested in this technology? Connect with our experienced licensing team to initiate the process.

Contact Us

Sign up for technology updates

Sign up now to receive the latest updates on cutting-edge technologies and innovations.

Sign Up

More Technologies

End-to-End Research and Development Assistance through First-Principles Model-Based Reasoning and Intelligent Test & Measurement

#25660
Dirk Englund
Artificial Intelligence (AI) and Machine Learning (ML) / Computer Science / Industrial Engineering & Automation

Generative Agents with Large Language Models

#25635
Guangyu Yang / Andrew Ahn / Kaiya Zhao / Michelangelo Naim
Artificial Intelligence (AI) and Machine Learning (ML)

Methods and Apparatuses to Track Hand Configurations based on Ultrasound Signals

#25586
Xuanhe Zhao / Gengxi Lu
Artificial Intelligence (AI) and Machine Learning (ML) / Biotechnology / Computer Science