|  |  |
 |
Anthony D. Rhodes Office: FAB 115 |
|---|
Academic Fields of Concentration
Machine Learning, Artificial Intelligence, Computer Vision, Numerical Analysis, Computational Mathematics, Intellectual History.
Education
Ph.D. Mathematical Sciences, Portland State University.
<>Focus: Machine Learning, Artificial Intelligence
<>Dissertation: "Leveraging Model Flexibility and Deep Structure: Non-Parametric and Deep Models for Computer Vision Processes with Applications to Deep Model Compression."
<>Advisors: Melanie Mitchell, Computer Science, Portland State University; Bin Jiang, Mathematics, Portland State University.
M.S. Computer Science, Portland State University.
M.S. Mathematics, Portland State University.
<>Foci: Computational Mathematics, Numerical Analysis, Algebra, Graph Theory, Topology.
<>Thesis: "The Algebraic Structure of Cellular Automata."
M.A. History, Philosophy and German Studies, Portland State University.
<>Focus: Modern European Intellectual History
<>Thesis: "Jacob Burckhardt: History and the Greeks in the Modern Context."
G.C.C.I. Graduate Certificate in Computational Intelligence, Portland State University.
G.C.A.S. Graduate Certificate in Applied Statistics, Portland State University.
B.A. Mathematics, with distinction, UC San Diego.
B.A. History, Minor: Classical Studies, with distinction, UC San Diego.
Publications
Rhodes, A.D., Ke Ding, Manan Goel, Amey Pawar, Sidharth Dhawan, and Narayan Sundararajan. Encoder-Decoder Based Interactive Image Segmentation with Inception-Atrous-Collation Blocks. (submitted)
Zamora, Julio, Anthony Rhodes, Lama Nachman. Fractional Adaptive Linear Units. AAAI Conference on Artificial Intelligence (AAAI), March 2022.
Zamora Esquivel, Julio, Anthony Rhodes, Jesus Cruz Vargas, Lama Nachman, Narayan Sundararajan. Convolution Filter Approximation Using Fractional Calculus.
International Conference on Computer Vision
2021, Workshop on Neural Architectures: Past, Present and Future (ICCV), October 2021. pdf
Rhodes, A.D., Jiang, B. Regularized L21-Based Semi-NonNegative Matrix Factorization. Data Compression Conference (DCC 2021), UT, USA, March 2021. pdf
Rhodes, A. D., Goel, M. High Fidelity Interactive Video Segmentation Using Tensor Decomposition, Boundary Loss, Convolutional Tessellations, and Context-Aware Skip Connections.
European Conference on Visual Median Production (CVMP 2020), London, UK, December 2020.
pdf
Rhodes, A. D. Evolving Order and Chaos: Comparing Particle Swarm Optimization and Genetic Algorithms for Global Coordination of Cellular Automata. IEEE Congress on Evolutionary Computation (IEEE CEC), Glasgow, Scotland, July, 2020. pdf
Rhodes, A. D. Search Algorithms for Mastermind. arXiv 1908.06183 pdf
Sennott, S., Akagi, L., Lee, M., & Rhodes, A. (in press) AAC and Artificial Intelligence (AI). Topics in Language Disorders. pdf
Rhodes, A. D., Goel, M. Deep Siamese Networks with Bayesian non-Parametrics for Video Object Tracking. Future Technologies Conference, San Francisco, November 2019. pdf
Rhodes, A. D., Goel, M. Tracking-Based Background Estimation for Object Segmentation and Video Inpainting [short paper]. SIGGRAPH European Conference on Visual Media Production (CVMP), London, UK, December 2018.
Rhodes, A. D. Real-Time Wind Noise Detection and Suppression with Neural-Based Signal Reconstruction for Multi-Channel, Low-Power Devices. pdf
Rhodes, A. D., Witte, J., Mitchell, M., and Jedynak, B. Gaussian Processes with Context-Supported Priors for Active Object Localization. Proceedings of the International Joint Conference
on Neural Networks (IJCNN), Rio de Janeiro, Brazil, July, 2018. pdf
Rhodes, A. D., Witte, J., Mitchell, M., and Jedynak, B. Bayesian optimization for refining object proposals. Proceedings of the International Conference on Image Processing Theory, Tools & Applications (IPTA), Montreal, Canada, 2017. pdf
Rhodes, A. D., Quinn, M. H., and Mitchell, M. Fast on-line kernel density estimation for active object localization. Proceedings of the International Joint Conference
on Neural Networks (IJCNN), Anchorage, AK, 2017. pdf
Quinn, M. H., Rhodes, A. D., and Mitchell, M. (2016). Active object localization in visual situations. arXiv 1607.00548. pdf
Patents
Rhodes, A.D., Ke Ding, Neil Yeung. Dual Attention Vision Transformers for Interactive Image Segmentation.
Rhodes, A.D., Giuseppe Raffa. Factorized Deformable 3D Convolutions with Temporal Squeeze-Excitation Modules for Video Action Recognition Workflows.
Rhodes, A.D. One Pass Lottery Ticket Pruning with Tensor Decomposition Revision for CNN Filter Compression.
Zamora Esquivel, Julio, Rhodes, Anthony, Dabby, Nadine and Cruz Vargas, Jesus. Generalized Activation Functions and Spike Train Activations.
Ke, Ding, Rhodes, A. D., and Goel, M. An Interactive Image Segmentation Network.
Rhodes, A. D. Learning Process Compression with Progressive Weight Freezing and Semi-Parametric Curve Extrapolation for Automated Machine Learning.
Rhodes, A. D., Ding, Ke, and Goel, M. IAC Block Architecture for Deep Convolutional Networks.
Rhodes, A. D., Ding, Ke, and Goel, M. Eidetic Memory Blocks with Wavelet Transforms and Low-Level Pre-Trained Features for Vision Tasks with Deep CNNs.
Rhodes, A. D., Goel, M. Extreme Fidelity Interactive Segmentation for Video Data with Deep Convolutional Tessellations and Context-Aware Skip Connections.
Rhodes, A. D. Automated Green Screen Segmentation for VFX Pipelines with Dynamic Gamma Correction for Low Light and Low Contrast Videos.
Rhodes, A. D., Goel, M. A Deep Learning Algorithm for Dense Semantic Semgnetation in Video with Automated Interactivity and Improved Temporal Coherence.
Rhodes, A. D., Goel, M. Efficient Video Tracking with Deep Siamese Networks and Bayesian Optimization.
Rhodes, A. D., Goel, M. Fine-Grain Object Segmentation Propagation in Video Data with Deep Features and Multi-Level Graphical Models.
Rhodes, A. D., Goel, M. High Resolution Interactive Video Segmentation Using Latent Diversity, Dense Feature Decomposition and Boundary Loss.
Rhodes, A. D., Goel, M., Kar, S., A Siamese Network-Based Deep Learning Technique for Rotoscopting Applications.
Rhodes, A. D., Kar, S., Efficient Wind Detection using Multiple Microphones for Headworn Devices.
Rhodes, A. D., Kar, S., Neural-Based Signal Reconstruction using Multiple Microphone for Headworn Devices.
Conferences and Presentations
<>"A Primer on Transformers and Vision Transformers", Intel Corporation, September 2021.
<>"Regularized Semi-Nonnegative Matrix Factorization Using L2,1-Norm for Data Compression", DCC 2021, UT, USA, MARCH 2021.
<>"High Fidelity Interactive Video Segmentation Using Tensor Decomposition, Boundary Loss, Convolutional Tessellations, and Context-Aware Skip Connections", CVMP 2020, London, UK, December 2020.
<>"Evolving Order and Chaos: Comparing Particle Swarm Optimization and Genetic Algorithms for Global Coordination of Cellular Automata", IEEE CEC, Glasgow, Scotland, July, 2020.
<>"A GANs Tutorial", Intel Corporation, Hillsboro, Oregon, September, 2019.
<>"Tracking-Based Background Estimation for Object Segmentation and Video Inpainting", CVMP, December, 2018, London, UK.
<>"Gaussian Processes with Context-Supported Priors for Active Object Localization, International
Conference on Neural Networks (IJCNN), July, 2018, Rio de Janeiro, Brazil.
<>"Computer Vision & Multi-Object Tracking", Intel Corporation, Hillsboro, Oregon, May, 2018.
<>"Dimensionality Reduction Methods for Machine Learning, guest lecture for graduate course in Statistical Learning III, STAT 610, PSU, March, 2018.
<>"Perceptrons and Neural Learningâ, guest lecture for graduate course in Statistical Learning II, STAT 610, PSU, February, 2018.
<>"Neural-Based Wind Noise Detection and Suppression for Low-Power Devices, PSU Seminar in Applied &
Computational Mathematics, Winter, 2018.
<>"Bayesian Optimization for Refining Object Proposals", Proceedings of the International Conference on Image
Processing Theory, Tools & Applications (IPTA),
November 2017, Montreal, Canada.
<>"Gaussian Processes with Context-Supported Priors for Active Object Localization, PSU
Statistics and Statistical Learning Seminar, May 2017.
<>"Bayesian Optimization for Refining Object Proposals, with an Application to Pedestrian
Detection, PSU Student Research Symposium, May 2017.
<>"Fast On-Line Kernel Density Estimation for Active Object Localization, International
Conference on Neural Networks (IJCNN), May 2017, Anchorage, AK.
<>"Machine Learning Classification & Support Vector Machines, guest lecture for graduate
course in CS: Machine Learning, April 2017.
<>"Graphical Models for Machine Learning, guest lecture for graduate course in Statistical
Learning, PSU, Winter 2017.
<>"A Primer on Bayesian Optimization for Active Object Localization in Computer Vision,
WSU Mathematics and Statistics Seminar, Fall 2016.
Some Papers and Lecture Materials
<>Computer Vision and Deep Learning Course Lectures
Part 1 Part 2
Part 3 Part 4 Part 5
Part 6 Part 7 Part 8
<>"A Primer on Transformers and Vision Transformers" pdf
<>"VAEs and GANs" slides
<>"Deep Learning: A Comprehensive Overview" slides
<>"Mathematical Preliminaries for AI/ML" slides
<>"Overview of AI/ML General Concepts" slides
<>"Foundations / History of AI" slides
<>"A Brief Intellectual History of Computing" slides
<>"Preliminaries for the Theory of Computation" slides
<>"Computer Vision & Multi-Object Tracking" slides
<>"Introduction to Deep Learning" slides
<>Advanced Topics in Machine Learning Course Lectures
Part 1 Part 2
Part 3 Part 4 Part 5
Part 6 Part 7 Part 8
Part 9
<>Machine Learning Course Lectures
Part 1 Part 2
Part 3 Part 4 Part 5
Part 6 Part 7 Part 8
Part 9
<>Theory of Computation Course Lectures
Part 1 Part 2
Part 3 Part 4 Part 5
Part 6 Part 7 Part 8
<>Algorithms & Complexity Course Letures
Part 1 Part 2
Part 3 Part 4 Part 5
Part 6 Part 7 Part 8
Part 9
<>A.I. Course Lectures Part 1 Part 2
Part 3 Part 4 Part 5
Part 6 Part 7 Part 8
Part 9 Part 10 Part 11
Part 12 Part 13 Part 14
Part 15 Part 16 Part 17
<>"Neural-Based Wind Noise Detection and Suppression for Low-Power Devices", slides
<>"Bayesian Optimization for Refining Object Proposals, with an Application to Pedestrian Detection", slides
<>"Graphical Models for Machine Learning", lecture notes
<>"Gaussian Process Regression for Visual Situation Recognition", slides
<>Lectures in Graph Theory and Complex Systems Part 1 Part 2
Part 3 Part 4 Part 5
Part 6 Part 7 Part 8
Part 9
<>Lectures in Numerical Analysis Part 1 Part 2 Part 3
Part 4 Part 5 Part 6 Part7
Part 8 Part 9 Part 10 Part 11
Part 12 Part 13 Part 14 Part 15
<>"The Algebraic Structure of Cellular Automata," pp. 28. PDF
<>"Jacob Burckhardt: History and the Greeks in the Modern Context," pp. 119. PDF
<>"A Statistical Analysis of Undergraduate Mathematics Placement Scores at Portland State University," pp. 19. PDF
<>"The Case Against Computational Theory of Mind: A Refutation of Mathematically-Contigent Weak A.I.," pp. 27.
University Teaching Experience
CS 250: Discrete Structures I
CS 251: Discrete Structures II
CS 350: Algorithms & Complexity
CS 410/510: Computer Vision & Deep Learning
CS 441/541: Artificial Intelligence
CS 445/545: Machine Learning
CS 446/546: Advanced Topics in Machine Learning
CS 581: Theory of Computation
Stat 243: Statistics/Probability I
Stat 244: Statistics II
Math 30: Pre-Algebra
Math 60: Algebra/Geometry I
Math 65: Algebra/Geometry II
Math 95: Intermediate Algebra/Geometry
Math 105: Exploring Mathematics
Math 107: Math & Society
Math 111: Pre-Calculus I
Math 112: Pre-Calculus II/Trigonometry
Math 171: Numerical Calculus I
Math 172: Numerical Calculus II
Math 221: Finite Mathematics
Math 241: Calculus for Business/Economics
Math 251: Calculus I
Math 252: Calculus II
Math 253: Calculus III
Math 254: Calculus IV
Math 256: Intro to Differential Equations
Math 261: Intro to Linear Algebra
Math 273: Vector Calculus
Math 300: Computational Mathematics & Numerical Analysis
Math 321: Ordinary Differential Equations
Math 398: History of Mathematics
[MOOC]: Matrix Algebra & Applications to Complex Systems
[MOOC]: Graph Theory/Network Theory & Applications to Complex Systems
Intel Corporation, PhD Technical Intern (2017).
Research Assistantship in Machine Learning and Visual Situation Recognition (Fall 2015-Spring 2017): Abstract
<> This project investigates a novel approach to building computer systems that can recognize visual situations;
the approach explored integrates two previously-studied approaches: brain-inspired neural networks for lower-lever
vision and cognitive-level models of concepts and analogy-making.
<> Project is funded by the National Science Foundation (NSF).
<> Advisor: Melanie Mitchell , Computer Science, Portland State University.
Lectures in Mathematics for Complex Systems Science (2014):
<> Content/curriculum creation for large-scale courses for http://www.complexityexplorer.org,
a web-based repository of educational materials related to complex systems science.
<>Advisor: Melanie Mitchell, Computer Science, Portland State University.
*Click image to view my lecture series for 'complexity explorer' MOOC*
*Calculus Lecture: Day One
