Greg Hamerly
Hankamer 330.20
Computer Science Department
Baylor University
One Bear Place #97141
Waco, TX 76798-7141, USA
Phone: +1-254-710-3876
Fax: +1-254-710-3889
Email: hamerly at cs dot baylor dot edu
I am a professor of computer science at Baylor University in Waco, Texas. On this webpage you can find more information about my research, teaching, schedule, publications, funding, and other things. Here is my Google Scholar page.
Research
Download our free app for automatically detecting white-eye in photos! White-eye in young children can be a symptom of retinoblastoma as well as other diseases.
My research is in machine learning, a sub-field of artificial intelligence. Some of the projects I'm involved in are:
- Automatically detecting and classifying leukocoria of the pupil in the eye from natural images. This is for early detection of negative conditions such as Retinoblastoma.
- Unsupervised learning methods (clustering, primarily), and improving algorithms like k-means to be faster, give better-quality results, or to act more intelligently (such as by finding the number of clusters).
- Applying machine learning to the task of optimizing computer program simulation, in the SimPoint project.
- Mixtures of naive Bayes models in unsupervised learning, for the detection of failures in hard drives.
Here is my NSF-funded research in developing a novel curriculum in computational thinking.
Here is my curriculum vitae, here are my publications, and here is my Ph.D. thesis.
Teaching
Course | Name | Links |
---|---|---|
CSI/STA 2300 | Intro to Data Science | S21 |
CSI 3334 | Data structures and algorithms | S24, F23, S23, S22, F21, S21, F20, S20, F19, S19, F18, F17, F16, F15, F14, F13, F11, S11, F10, S10, F09, S09, F08, S08, F07, S07, F06, S06, F05, F04 |
CSI 4144 | Competitive learning I/II/III | F22, S22, F21, S21, F20, S20, F19, S19, F18, F17, S17, F16, S16, F15, S15, F14, S14, F13, S13, F12, S12, S11, F10, S10, F08, S08, F07, S07, F06, S06, F05 |
CSI 4330 | Foundations of computing | F24 F12 |
CSI 5310 (formerly 4336) | Computer science theory | F24, F22, F21, F20, F19, F18, F17, F16, F15, F14, F13, F12, F11, F10, F09, F08, F07, F06, F05 |
CSI 5010 | Graduate Seminar (jointly held with 4010) | F14, F13, F12, F11 |
CSI 5325 | Introduction to Machine Learning | S25, S23, S22, S20, S19, S18, S17, S16, S15, S14, S13, S12, S11, S10, S09, S08, S07, S06, S05 |
Schedule and Office Hours
My office hours for Spring 2025 are:
- Monday, Wednesday, and Friday from 13:30-14:30. You do not need to make an appointment to attend my office hours.
- If you cannot attend my office hours, you may make an appointment for another time.
To make an appointment for a meeting outside of my office hours, please first consult my Outlook Calendar (linked below) and find a reasonable time (within business hours) that I am available. Then send me an Outlook Calendar invitation for meeting, preferably at least a day in advance of when you want to meet. Please schedule only the amount of time you think you'll need (e.g. 10-15 minutes for a student meeting).
Student meetings and office hours are in my office, but could be online if you prefer (you may chat with me via Microsoft Teams). Due to my busy and changing schedule, some office hours may be delayed or cancelled without notice.
Here is my Outlook Calendar that you can view in a separate page. It defaults to a monthly view; you can see more details by selecting a weekly / daily view.
Publications
- Active Learning Strategy Using Contrastive Learning and K-Means for Aquatic Invasive Species Recognition. In The Maritime Computer Vision Workshop of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2024. , , .
- Analysis of an optical imaging system prototype for autonomously monitoring zooplankton in an aquaculture facility. Aquacultural Engineering, Volume 104, 2023. , , , , , , , , , .
- Is ReLU Adversarially Robust?. In proceedings of the LatinX in AI Workshop at ICML, 2023. , , .
- Video-Based Recognition of Aquatic Invasive Species Larvae Using Attention-LSTM Transformer. In proceedings of the International Symposium on Visual Computing, 2023. , , , .
- Recognition of Aquatic Invasive Species Larvae using Autoencoder-based Feature Averaging. In proceedings of the International Symposium on Visual Computing, 2022. , .
- Clustering Faster and Better with Projected Data. In proceedings of the 6th International Conference on Information System and Data Mining, 2022. [pdf] , .
- Autonomous early detection of eye disease in childhood photographs In Science Advances, 2019. [web, pdf] , , , , , , , , , , .
- Geometric methods to accelerate k-means algorithms At SDM 2016, 2016. [pdf, supplementary graphs] , .
- Detection of leukocoria using a soft fusion of expert classifiers under non-clinical settings. In BMC Opthamology, 2014. , , , .
- Accelerating Lloyd's algorithm for k-means clustering. Chapter in Partitional Clustering Algorithms (Springer), 2014. [pdf] , .
- A Convolutional Neural Network Approach for Classifying Leukocoria. In proceedings of the 2014 Southwest Symposium on Image Analysis and Interpretation (SSIAI), April, 2014. [pdf] , , , .
- Finding the Smallest Circle Containing the Iris in the Denoised Wavelet Domain. In proceedings of the 2014 Southwest Symposium on Image Analysis and Interpretation (SSIAI), April, 2014. [pdf] , , , .
- Colorimetric Image Analysis in Detection of Leukocoria from Retinoblastoma in Snapshots Taken by Standard Digital Photography. Meeting Abstract. In Investigative Ophthalmology & Visual Science June 2013. Volume 54, Issue 15, Page 1584. , , , , , , , , ,
- Accelerated k-means with adaptive distance bounds. In OPT2012: the 5th NIPS Workshop on Optimization for Machine Learning, December, 2012. [pdf] , .
- Computational Thinking: Building a Model Curriculum In ACET Journal of Computer Education and Research, 2012. [pdf] , , , , .
- Representative Sampling Using SimPoint. Chapter 10 in the book Processor and System-on-Chip Simulation, edited by Rainer Leupers and Olivier Temam; published by Springer, 2010. , , , ,
- Efficient Model Selection for Large-Scale Nearest-Neighbor Data Mining In proceedings of the 2010 British National Conference on Databases (BNCOD 2010), June 2010. [pdf] , ,
- Making k-means even faster In proceedings of the 2010 SIAM international conference on data mining (SDM 2010), April 2010. [pdf] ,
- Hierarchical Stability-Based Model Selection For Clustering Algorithms In proceedings of the International Conference on Machine Learning and Applications, December 2009. , ,
- Improving SimPoint accuracy for small simulation budgets with EDCM clustering In proceedings of the Second workshop on Statistical and Machine learning approaches to ARchitectures and compilaTion (SMART '08), January 2008. [pdf] , ,
- Cross Binary Simulation Points In Proceedings of the International Symposium on Performance Analysis of Systems and Software (ISPASS-2007) March 2007. [pdf] , , , , , ,
- PG-means: learning the number of clusters in data. In proceedings of the twentieth annual conference on neural information processing systems (NIPS), December 2006. [ps, pdf] , ,
- Using Machine Learning to Guide Architecture Simulation. Journal of Machine Learning Research, Volume 7, Pages 343-378, 2006. [abstract, pdf] , , , , ,
- Comparing Multinomial and K-means clustering for SimPoint. In the 2006 IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS-2006), 2006. [abstract, pdf] , , ,
- SimPoint 3.0: Faster and more flexible program analysis. Journal on Instruction-Level Parallelism (JILP), September, 2005. [pdf] , , , ,
- SimPoint 3.0: Faster and more flexible program analysis. Workshop on Modeling, Benchmarking and Simulation (MoBS), June 2005. [abstract, pdf] , , , ,
- SimPoint: Picking Representative Samples to Guide Simulation. Chapter 7 in the book Performance Evaluation and Benchmarking, edited by Lizy Kurian John and Lieven Eeckhout; published by CRC Press, 2005. , , , ,
- Motivation for variable length intervals and hierarchical phase behavior. In the 2005 IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS-2005), March 2005. [abstract, pdf] , , , , ,
- The strong correlation between code signatures and performance. In the 2005 IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS-2005), March 2005. [abstract, pdf] , , , , ,
- Exploring perceptron-based register value prediction. In the second value-prediction and value-based optimization workshop, October 2004. [pdf] , ,
- How to use SimPoint to pick simulation points. In ACM SIGMETRICS Performance Evaluation Review, Volume 31(4), March 2004. [abstract, pdf] , , ,
- Discovering and Exploiting Program Phases. In IEEE Micro: Micro's top picks from computer architecture conferences, November-December 2003 (Vol. 23, No. 6) [pdf]. , , , , ,
- Learning the k in k-means. In proceedings of the seventeenth annual conference on neural information processing systems (NIPS), pages 281-288, December 2003. [ps, pdf] (Older UCSD technical report CS2002-0716 [ps]) , ,
- Picking Statistically Valid and Early Simulation Points. In proceedings of the international conference on parallel architectures and compilation techniques (PACT), September 2003. [abstract, pdf] , , ,
- Using SimPoint for Accurate and Efficient Simulation. In proceedings of the international conference on measurement and modeling of computer systems (SIGMETRICS), June 2003. [abstract, pdf] , , , , ,
- Automatically characterizing large scale program behavior. In proceedings of the tenth international conference on architectural support for programming languages and operating systems (ASPLOS), October 2002. [abstract, pdf] , , , ,
- Alternatives to the k-means algorithm that find better clusterings. In proceedings of the ACM conference on information and knowledge management (CIKM), pages 600-607, November 2002. [ps] (Older UCSD technical report CS2002-0702 [ps]) , ,
- Bayesian approaches to failure prediction for disk drives. In proceedings of the eighteenth international conference on machine learning (ICML), June 2001. [ps] , ,
Here are links to my coauthors and collaborators:
, , , , , , , , , , , .An upper bound on my Erdős number is 4. One such path is me → Charles Elkan → Russell Greiner → Michael S. O. Molloy → Paul Erdős. Another such path is me → Tim Sherwood → Ömer Eğecioğlu → Charles Ryavec → Paul Erdős.
Thesis
Defended on June 26, 2003.
Learning structure and concepts in data through data clustering.
[ps, 1.8MB]
[pdf, 3.6MB]
Thanks to Tom Stepleton at Sony Japan for catching a typo in one of my
equations.
Funding
My research and teaching work has been generously supported by the following:
- US Department of the Interior, via Bureau of Reclamation (2024-2025)
- National Institutes of Health (2024-2029)
- Texas Parks and Wildlife Department (2021-2023)
- National Science Foundation (2010-2012, 2019-2025)
- Intel Corporation
- Baylor University Young Investigator's Development Program, University Research Council, and Undergraduate Research and Scholarly Achievement programs
Current and former students
- Jan Sladek, M.S. 2017
- Vaclav Cibur, M.S. 2016
- James Boer, M.S. 2016
- Petr Ryšavý, M.S. 2015
- Ryan Yan, M.S. expected 2015
- Ryan Henning, M.S. 2014
- Paniz Karbasi, M.S. 2014, working on a Ph.D. in ECE at Baylor
- Li Guo, M.S. 2014
- Pablo Rivas-Perea, postdoc (2012-2015)
- Jonathan Drake, M.S. 2013, Undergraduate Scholars Thesis 2011
- Tak-Chien Chiam, M.S. 2012, currently at Amazon
- Hao Guo, M.S. 2012
- George Montanez, M.S. 2011, working on a Ph.D. at Carnegie Mellon
- Winston Ewert, M.S. 2011, now at Google
- Lei Meng, M.S. 2011, working on a Ph.D. at Notre Dame
- Bing Yin, M.S. 2009, currently at Amazon
- Josh Johnston, M.S. 2007
- Yu Feng, M.S. 2006, currently at Microsoft
Current/former Affiliations
- I am a member of ACM
- DTAI group at the KU Leuven computer science department
- AI lab at the UCSD computer science department
- Computer science department at CalPoly, San Luis Obispo
Programming contests
- I went to the ICPC world finals as a contestant for UC San Diego in 2000 and 2001.
- I have been a coach for students at UCSD and Baylor.
- I regularly teach Competitive Learning at Baylor, a course on how to do algorithmic problem solving. I developed this course with David Sturgill, and together we have authored more than 300 problems for the course.
- I participated in putting together the following contests:
- The 2009 ICPC World Finals Playoff.
- Since 2010: practice problems at the ICPC World Finals.
- For 2020, I have not planned the North American Qualifier; others have done that. Please see this ICPC page on the 2020 NAQ which will be in February 2021 (but I am not involved in running it).
- Past North American Qualifiers: 2019 NAQ, 2018 NAQ, 2017 NAQ, 2016 NAQ, 2015 NAQ, 2014 NAQ, 2013 NAQ, 2012 NAQ.
- Chief Judge for the ICPC South Central USA regional competition: 2018, 2019.
- I have been a site director for the ICPC South Central USA regional competition in 2010-2013, 2015-2019.
- I was been a member of the ICPC Live Analytics team at the ICPC world finals from 2011-2015.
Links to other things I've done
- Some sites I frequent are in my bookmarks.
- Here is a list of software I have written and released.
- I have received various dubious awards in my career.
- I have a few Mastodon accounts: mastodon.world/@ghamerly, sigmoid.social/@ghamerly, mathstodon.xyz/@ghamerly.
Copyright © 2004 Greg Hamerly
Computer Science Department
Baylor University