Michael R. Smith

Michael R. Smith

Auto-generated profile, based on publicly available information

Michael R. Smith

Department of Computer Science Brigham Young University Provo 84602 UT

Research Focus & Metrics

Academic Career Length

16Years (2011-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
5 November 2013 in Machine Learning
Verified
Journal Article
Closed access
PDF file
MSMichael R. Smith
Michael R. Smith
TMTony Martinez
Tony Martinez
CGChristophe Giraud-Carrier
Christophe Giraud-Carrier

1 July 2011
Verified
Conference Paper
Closed access
MSMichael R. Smith
Michael R. Smith
TMTony Martinez
Tony Martinez
Appropriately handling noise and outliers is an important issue in data mining. In this paper we examine how noise and outliers are handled by learning algorithms. We introduce a filtering method called PRISM that identifies and removes instances that should be misclassified. We refer to the set of removed instances as ISMs (instances that should be misclassified). We examine PRISM and compare it against 3 existing outlier detection methods and 1 noise reduction technique on 48 data sets using 9 learning algorithms. Using PRISM, the classification accuracy increases from 78.5% to 79.8% on a set of 53 data sets and is statistically significant. In addition, the accuracy on the non-outlier instances increases from 82.8% to 84.7%. PRISM achieves a higher classification accuracy than the outlier detection methods and compares favorably with the noise reduction method.

12 July 2014 in Computational Intelligence
Verified
Journal Article
Closed access
PDF file
MSMichael R. Smith
Michael R. Smith
TMTony Martinez
Tony Martinez

1 May 2017
Verified
Conference Paper
Open access
MSMichael R. Smith
Michael R. Smith
AHAaron J. Hill
Aaron J. Hill
KCKristofor D. Carlson
Kristofor D. Carlson
CVCraig M. Vineyard
Craig M. Vineyard
JDJonathon Donaldson
Jonathon Donaldson
JAJames B. Aimone
James B. Aimone
Information in neural networks is represented as weighted connections, or synapses, between neurons. This poses a problem as the primary computational bottleneck for neural networks is the vector-matrix multiply when inputs are multiplied by the neural network weights. Conventional processing architectures are not well suited for simulating neural networks, often requiring large amounts of energy and time. Additionally, synapses in biological neural networks are not binary connections, but exhibit a nonlinear response function as neurotransmitters are emitted and diffuse between neurons. Inspired by neuroscience principles, we present a digital neuromorphic architecture, the Spiking Temporal Processing Unit (STPU), capable of modeling arbitrary complex synaptic response functions without requiring additional hardware components. We consider the paradigm of spiking neurons with temporally coded information as opposed to non-spiking rate coded neurons used in most neural networks. In this paradigm we examine liquid state machines applied to speech recognition and show how a liquid state machine with temporal dynamics maps onto the STPU - demonstrating the flexibility and efficiency of the STPU for instantiating neural algorithms.

1 July 2014 in Computational Intelligence
Verified
Journal Article
Closed access
PDF file
MGMichael S. Gashler
Michael S. Gashler
MSMichael R. Smith
Michael R. Smith
RMRichard Morris
Richard Morris
TMTony Martinez
Tony Martinez

19 December 2013 in arXiv
Verified
Preprint
Open access
PDF file
MGMichael S. Gashler
Michael S. Gashler
MSMichael R. Smith
Michael R. Smith
RMRichard Morris
Richard Morris
TMTony Martinez
Tony Martinez
Many data mining and data analysis techniques operate on dense matrices or complete tables of data. Real-world data sets, however, often contain unknown values. Even many classification algorithms that are designed to operate with missing values still exhibit deteriorated accuracy. One approach to handling missing values is to fill in (impute) the missing values. In this paper, we present a technique for unsupervised learning called Unsupervised Backpropagation (UBP), which trains a multi-layer perceptron to fit to the manifold sampled by a set of observed point-vectors. We evaluate UBP with the task of imputing missing values in datasets, and show that UBP is able to predict missing values with significantly lower sum-squared error than other collaborative filtering and imputation techniques. We also demonstrate with 24 datasets and 9 supervised learning algorithms that classification accuracy is usually higher when randomly-withheld values are imputed using UBP, rather than with other methods.