ACCEPTED PEER REVIEWED PUBLICATIONS

2019

SemiHD: Semi-Supervised Learning Using Hyperdimensional Computing


2019

AdaptHD: Adaptive Efficient Training for Brain-Inspired Hyperdimensional Computing

  • Conference: BioCAS 2019 - IEEE Biomedical Circuits and Systems
  • Work at University of California, San Diego and EPFL, Lausanne
  • Group of prof. Tajana S. Rosing and Giovanni De Micheli
  • AdaptHD introduces the definition of learning rate in HD computing and proposes two approaches for adaptive training: iteration-dependent and data-dependent. In the iteration-dependent approach, AdaptHD uses a large learning rate to speedup the training procedure in the first iterations, and then adaptively reduces the learning rate depending on the slope of the error rate.

2019

CompHD: Efficient Hyperdimensional Computing Using Model Compression


2018

Particle shape accounts for instrumental discrepancy in ice core dust size distributions


CURRENTLY UNDER REVIEW

Most of the preprints aren't available on arXiv, but you can always contact me for more info!

2019

QuantHD: A Quantization Framework for FPGA Acceleration of Hyperdimensional Computing

  • Work at University of California, San Diego
  • Group of prof. Tajana S. Rosing
  • We invented a new machine learning algorithm which can achieve on average 34.1x and 4.1x energy efficiency improvement on training and testing respectively, and 8.2x and 13.4x faster computing in training and testing. This is compared to the previous state-of-the-art HD computing ML algorithms. It provides similar classification accuracy as low-cost state-of-the-art Machine Learning algorithms, while significantly improving the energy efficiency. 

2019

Bit-Serial HD: Approximate Hyperdimensional Computing in Machine Learning

  • Work at University of California, San Diego and EPFL
  • Groups of Prof. Tajana S. Rosing (UCSD) and Prof. Giovanni De Micheli (EPFL)
  • We invented a new HD computing acceleration framework, which significantly reduces the power consumption of Machine Learning algorithms, while maintaining almost the same classification accuracy 

2019

LookHD: Acceleration of Hyperdimensional Computing Exploiting Computation Reuse

  • Work at University of California, San Diego
  • Group of prof. Tajana S. Rosing
  • We invented LookHD: a method which compresses a HD algorithm matrix into a single vector without significantly decreasing classification accuracy. This method is 2.2x faster and 4.1x more energy efficient, as compared to existing HD computing algorithms

DRAFTS

2019

Quantum computational finance: martingale asset pricing and Pauli games

  • Work at Centre for Quantum Technologies, National University of Singapore
  • Group of Dr. Patrick Rebentrost
  • Contribution: We exhibit a quantum algorithm for the pricing of financial assets and derivatives

2019

Bell Diagonal and Werner state generation: entanglement and discord witnesses on the IBM quantum computer

  • Work at EPFL
  • Contribution: We developed a circuit for creating Bell Diagonal and Werner states

2019

Global increase in atmospheric dust content over the last 300 years

  • Work at Niels Bohr Institute, University of Copenhagen
  • Group of Prof. Dorthe Dahl-Jensen & Prof. Paul Vallelonga
  • Contribution: discovery of a large increase in atmospheric dust content, which might have significant impact on our planet's climate