Supervised Learning
In supervised learning the desired outputs are known for each input, and the task is to learn a mapping between them that generalizes well to new inputs. Our research in this area includes various applications of neural networks and related methods.
     [Expand to show all 33][Minimize]
NeuroComb: Improving SAT Solving with Graph Neural Networks Wenxi Wang, Yang Hu, Mohit Tiwari, Sarfraz Khurshid, Kenneth McMillan, Risto Miikkulainen In Proceedings of the International Conference on Learning Representations, 2024. (also arX... 2024

Pandemic Resilience: Developing an AI-calibrated Ensemble of Models to Inform Decision Making GPAI Technical Report, Global Partnership on Artificial Intelligence, December 2023. 2023

Efficient Activation Function Optimization through Surrogate Modeling Garrett Bingham and Risto Miikkulainen In Proceedings of the 23rd Conference on Neural Information Processing Systems (NeurIPS 2023)... 2023

Evolutionary Supervised Machine Learning Risto Miikkulainen In W. Banzhaf, P. Machado, and M. Zhang, editors, Handbook of Evolutionary Machine Learning, ... 2023

AutoInit: Analytic Signal-Preserving Weight Initialization for Neural Networks Garrett Bingham and Risto Miikkulainen In Proceedings of the 37th AAAI Conference on Artificial Intelligence, 2023. (also arXiv:20... 2023

Detecting Misclassification Errors in Neural Networks with a Gaussian Process Model Xin Qiu and Risto Miikkulainen In Proceedings of the 36th AAAI Conference on Artificial Intelligence (AAAI-2022), 2022. (A... 2022

Discovering Parametric Activation Functions Garrett Bingham and Risto Miikkulainen Neural Networks, 148:48-65, 2022. 2022

Regularized Evolutionary Population-Based Training Jason Liang, Santiago Gonzalez, Hormoz Shahrzad, and Risto Miikkulainen In Proceedings of the Genetic and Evolutionary Computation Conference, 323-331, 2021. 2021

Optimizing Loss Functions Through Multivariate Taylor Polynomial Parameterization Santiago Gonzalez and Risto Miikkulainen In Proceedings of the Genetic and Evolutionary Computation Conference, 305-313, 2021. 2021

The Traveling Observer Model: Multi-task Learning Through Spatial Variable Embeddings Elliot Meyerson and Risto Miikkulainen To Appear In International Conference on Learning Representations, 2021. 2021

Improving Neural Network Learning Through Dual Variable Learning Rates Elizabeth Liner, Risto Miikkulainen In Proceedings of the International Joint Conference on Neural Networks, 2021. 2021

Effective Regularization Through Loss-Function Metalearning Santiago Gonzalez and Risto Miikkulainen In arXiv:2010.00788, 2021. 2021

Improved Training Speed, Accuracy, and Data Utilization Through Loss Function Optimization Santiago Gonzalez and Risto Miikkulainen In Proceedings of the 2020 IEEE Congress on Evolutionary Computation (CEC), 1-8, July 2020. 2020

Evolutionary Optimization of Deep Learning Activation Functions Garrett Bingham, William Macke, and Risto Miikkulainen In Genetic and Evolutionary Computation Conference (GECCO '20), 289-296, Cancun, Mexico, 20... 2020

Quantifying Point-Prediction Uncertainty in Neural Networks via Residual Estimation with an I/O Kernel Xin Qiu, Elliot Meyerson, Risto Miikkulainen In International Conference on Learning Representations, 2020. 2020

From Nodes to Networks: Evolving Recurrent Neural Networks Aditya Rawal, Risto Miikkulainen In H. Iba and N. Noman, editors, Deep Neural Evolution: Deep Learning with Evolutionary Computati... 2020

Improving Deep Learning Through Loss-Function Evolution Santiago Gonzalez PhD Thesis, Department of Computer Science, The University of Texas at Austin, 2020. 2020

The Traveling Observer Model: Multi-task Learning Through Spatial Variable Embeddings Elliot Meyerson and Risto Miikkulainen arxiv:2010.02354, October 2020. 2020

Evolving Deep Neural Networks Risto Miikkulainen, Jason Liang, Elliot Meyerson, Aditya Rawal, Dan Fink, Olivier Francon, Bala Raju... In Robert Kozma, Cesare Alippi, Yoonsuck Choe, and Francesco Carlo Morabito, editors, Artificial ... 2019

Pseudo-task Augmentation: From Deep Multitask Learning to Intratask Sharing---and Back Elliot Meyerson, Risto Miikkulainen In Proceedings of the 35th International Conference on Machine Learning, 739-748, 2018. 2018

Discovering Gated Recurrent Neural Network Architectures Aditya Rawal PhD Thesis, Department of Computer Science, The University of Texas at Austin, Austin, TX 78712, 201... 2018

Learning Useful Features For Poker Arjun Nagineni Technical Report, Department of Computer Sciences, The University of Texas at Austin, Austin, TX, 20... 2018

Beyond Shared Hierarchies: Deep Multitask Learning through Soft Layer Ordering Elliot Meyerson and Risto Miikkulainen In Proceedings of the Sixth International Conference on Learning Representations (ICLR), Vanc... 2018

Efficient Sampling for Design Optimization of an SLS Product Nancy Xu, Cem C. Tutum In Proceedings of the 28th Annual International Solid Freeform Fabrication Symposium, 12, Aus... 2017

Surrogate-based Evolutionary Optimization for Friction Stir Welding Cem C Tutum, Shaayaan Sayed and Risto Miikkulainen In Proceedings of IEEE World Congress on Computational Intelligence (WCCI 2016), 8 pages, Van... 2016

GRADE: Machine Learning Support for Graduate Admissions Austin Waters, Risto Miikkulainen AI Magazine, 35:64-75, 2014. 2014

Infinite-Word Topic Models for Digital Media Austin Waters PhD Thesis, Department of Computer Science, The University of Texas at Austin, 2014. 2014

GRADE: Machine Learning Support for Graduate Admissions Austin Waters, Risto Miikkulainen In Proceedings of the 25th Conference on Innovative Applications of Artificial Intelligence, ... 2013

Accelerating Evolution via Egalitarian Social Learning Wesley Tansey, Eliana Feasley, and Risto Miikkulainen In Proceedings of the 14th Annual Genetic and Evolutionary Computation Conference (GECCO 2012) 2012

Temporal Convolution Machines for Sequence Learning Alan J Lockett and Risto Miikkulainen Technical Report AI-09-04, Department of Computer Sciences, the University of Texas at Austin, 2009. 2009

Detecting Motion in the Environment with a Moving Quadruped Robot Peggy Fidelman, Thayne Coffman and Risto Miikkulainen In Gerhard Lakemeyer and Elizabeth Sklar and Domenico Sorenti and Tomoichi Takahashi, editors, Ro... 2007

Learning Concept Drift with a Committee of Decision Trees Kenneth O. Stanley Technical Report AI03-302, Department of Computer Sciences, The University of Texas at Austin, 2003. 2003

Parsing Embedded Clauses with Distributed Neural Networks Risto Miikkulainen and Dennis Bijwaard In Proceedings of the Twelfth National Conference on Artificial Intelligence, 858-864, Januar... 1994

     [Expand to show all 14][Minimize]
Garrett Bingham Ph.D. Alumni bingham [at] cs utexas edu
Eliana Feasley Former Ph.D. Student elie [at] cs utexas edu
Peggy Fidelman Former Ph.D. Student peggyf [at] cs utexas edu
Olivier Francon Collaborator olivier francon [at] cognizant com
Kim Houck Ph.D. Alumni houck [at] cs utexas edu
Alan J. Lockett Ph.D. Alumni alan lockett [at] gmail com
Risto Miikkulainen Faculty risto [at] cs utexas edu
Arjun Nagineni Undergraduate Alumni arjun nagineni [at] utexas edu
Xin Qiu Collaborator xin qiu [at] cognizant com
Vito Ruiz Masters Alumni
Jake Ryan Undergraduate Alumni
Kenneth Stanley Postdoctoral Alumni kstanley [at] cs ucf edu
Wesley Tansey Former Collaborator tansey [at] cs utexas edu
Austin Waters Ph.D. Alumni austin [at] cs utexas edu
ESL This is the C# source code for the experiments with Egalitarian Social Learning (ESL) in a robot foraging domain. The re... 2012