Daniel Brown
Syracuse University
5 Papers
10 Citations
Daniel Brown is an academic researcher from Syracuse University. The author has contributed to research in topics: TrueNorth & Neuromorphic engineering. The author has an hindex of 2, co-authored 5 publications.
Chat about Author
Papers
SAR object classification implementation for embedded platforms
Chris Capraro,Uttam Majumder,Josh Siddall,Eric K. Davis,Daniel Brown,Chris Cicotta +5 more
- 11 Jun 2019
TL;DR: An algorithm to reduce the run-time and the power consumption of Deep Neural Networks (DNNs) classifiers by reducing the DNN model size required for a given object classification task is developed.
5
Patent
System and method for reinstalling, upgrading or downgrading an operating system
Daniel Brown,Karl David Mortensen +1 more
- 06 Feb 2015
TL;DR: In this article, a method and device for installing, reinstalling, upgrading, or downgrading an operating system is presented, including the steps of mounting, on a computing device having a primary memory and a secondary memory storing a first operating system, a virtual disk in the primary memory; installing, on the virtual disk an installation operating system; staging in primary memory a desired operating system.
3
Demonstrating Advanced Machine Learning and Neuromorphic Computing Using IBM’s NS16e
Mark Barnell,Courtney Raymond,Matthew Wilson,Darrek Isereau,Eric Cote,Daniel Brown,Chris Cicotta +6 more
- 16 Jul 2020
TL;DR: For the first time ever, an advanced scalable computing architecture was demonstrated using 16 TrueNorth neuromorphic processors containing in aggregate over 16 million neurons, used to demonstrate new ML techniques including the exploitation of optical and radar sensor data simultaneously, while consuming a fraction of the power compared to traditional Von Neumann computing architectures.
2
An approaches for noise induced object classifications accuracy improvement
Eric K. Davis,Uttam Majumder,Chris Capraro,Chris Cicotta,Josh Siddall,Daniel Brown +5 more
- 31 May 2019
TL;DR: This research proposes image pre-processing to reduce the impact of noise induced low classification accuracy and compares the object recognition accuracy of a pretrained model on pre-processed noisy images and unprocessed noise images.
1
Low Power Computing and Simultaneous Electro-Optical/Radar Data Processing using IBM’s NS16e 16-chip Neuromorphic Hardware
Mark Barnell,Courtney Raymond,Daniel Brown,Matthew Wilson,Eric Cote +4 more
- 01 Sep 2019
TL;DR: For the first time ever, advanced machine learning compute architectures, techniques, and methods were demonstrated on United States Geological Survey optical imagery and Department of Defense Synthetic Aperture Radar imagery, simultaneously, using IBM’s new NS16e neurosynaptic processor board comprised of 16 TrueNorth chips.