Tag: Geometric Multi-resolution Analysis

Neural Network Optimization with Biologically Inspired Low-Dimensional Manifold Learning

Hieu Le, Andrew Wood, Sylee Dandekar, Sang (Peter) Chin

Publication:

2021 International Conference on Computational Science and Computational Intelligence (CSCI) (Conference Paper)

DOI
Cite

@inproceedings{le_neural_2021,
abstract = {Neural Networks learn to recognize and leverage patterns in data. In most cases, while data is represented in a high-dimensional space, the patterns within the data exist along a manifold in a small subset of those dimensions. In this paper, we show that by using a biologically inspired algorithm called Geometric Multi-Resolution Analysis (GMRA), these low-dimensional manifolds can be computed and can be used to convert datasets into more useful forms for learning. We also show that, thanks to the lower-dimensional representation of the converted datasets, that smaller networks can achieve state-of-the-art performance while using significantly fewer parameters.},
author = {Le, Hieu and Wood, Andrew and Dandekar, Sylee and Chin, Peter},
booktitle = {2021 International Conference on Computational Science and Computational Intelligence (CSCI)},
doi = {10.1109/CSCI54926.2021.00006},
month = {December},
pages = {8–13},
title = {Neural Network Optimization with Biologically Inspired Low-Dimensional Manifold Learning},
year = {2021}
}

Non-Volatile Memory Accelerated Geometric Multi-Scale Resolution Analysis

Andrew Wood, Moshik Hershcovitch, Daniel Waddington, Sarel Cohen, Meredith Wolf, Hongjun Suh, Weiyu Will Zong, Sang (Peter) Chin

Publication:

2021 IEEE High Performance Extreme Computing Conference (HPEC) (Conference Paper)

DOI
Cite

@inproceedings{wood_non-volatile_2021,
abstract = {Dimensionality reduction algorithms are standard tools in a researcher’s toolbox. Dimensionality reduction algorithms are frequently used to augment downstream tasks such as machine learning, data science, and also are exploratory methods for understanding complex phenomena. For instance, dimensionality reduction is commonly used in Biology as well as Neuroscience to understand data collected from biological subjects. However, dimensionality reduction techniques are limited by the von-Neumann architectures that they execute on. Specifically, data intensive algorithms such as dimensionality reduction techniques often require fast, high capacity, persistent memory which historically hardware has been unable to provide at the same time. In this paper, we present a re-implementation of an existing dimensionality reduction technique called Geometric Multi-Scale Resolution Analysis (GMRA) which has been accelerated via novel persistent memory technology called Memory Centric Active Storage (MCAS). Our implementation uses a specialized version of MCAS called PyMM that provides native support for Python datatypes including NumPy arrays and PyTorch tensors. We compare our PyMM implementation against a DRAM implementation, and show that when data fits in DRAM, PyMM offers competitive runtimes. When data does not fit in DRAM, our PyMM implementation is still able to process the data.},
author = {Wood, Andrew and Hershcovitch, Moshik and Waddington, Daniel and Cohen, Sarel and Wolf, Meredith and Suh, Hongjun and Zong, Weiyu and Chin, Peter},
booktitle = {2021 IEEE High Performance Extreme Computing Conference (HPEC)},
doi = {10.1109/HPEC49654.2021.9622854},
month = {September},
note = {ISSN: 2643-1971},
pages = {1–7},
title = {Non-Volatile Memory Accelerated Geometric Multi-Scale Resolution Analysis},
year = {2021}
}

Geometric multi-resolution analysis based classification for high dimensional data

Dung N. Tran, Sang (Peter) Chin

Publication:

Cyber Sensing 2014 (Conference Paper)

DOI
Cite

@inproceedings{tran_geometric_2014,
abstract = {Data sets are often modeled as point clouds lying in a high dimensional space. In practice, they usually reside on or near a much lower dimensional manifold embedded in the ambient space; this feature allows for both a simple representation of the data as well as accurate performance for statistical inference procedures such as estimation, regression and classification. In this paper we propose a framework based on geometric multi-resolution analysis (GMRA) to tackle the problem of classifying data lying around a low-dimensional set M embedded in a high-dimensional space R$^\textrmD$. We test our algorithms on real data sets and demonstrate its efficacy in the presence of noise.},
author = {Tran, Dung N. and Chin, Sang Peter},
booktitle = {Cyber Sensing 2014},
doi = {10.1117/12.2063316},
editor = {Ternovskiy, Igor V. and Chin, Peter},
keywords = {Classification, Dimension Reduction, Geometric Multi-resolution Analysis, High Dimensional Data, Low Intrinsic Dimension, Manifold Learning},
note = {Backup Publisher: International Society for Optics and Photonics},
pages = {132 — 139},
publisher = {SPIE},
title = {Geometric multi-resolution analysis based classification for high dimensional data},
url = {https://doi.org/10.1117/12.2063316},
volume = {9097},
year = {2014}
}