My name is Luke Godfrey. I am a currently a Machine Learning Researcher at SupplyPike.
I research machine learning with a particular focus on artificial neural networks and their applications. I am interested in the application of neural networks to time-series analysis and forecasting, nonlinear dimensionality reduction, and reinforcement learning. Much of my work involves the use of parametric and other non-traditional activation functions to reduce training time, improve generalization, and increase transparency in neural networks.
Godfrey, Luke B. and Michael S. Gashler. 2018. “Leveraging Product as an Activation Function in Deep Networks.” In Systems, Man and Cybernetics, 2018 IEEE International Conference on. Miyazaki, Japan: IEEE.
Sha, Zhenghui, Luke B. Godfrey, and Michael S. Gashler. 2018. “Modeling Sequential Design Decisions Using Fine-Grained Empirical Data.” In Design Science Research 2018: Workshop on Data Driven Design and Learning. Montreal, Canada.
Godfrey, Luke B. and Michael S. Gashler. 2018. “
Neural decomposition of time- series data for effective generalization.” IEEE Transactions on Neural Networks and Learning Systems 29, no. 7 (2018): 2973-2985. IEEE.
Godfrey, Luke B. and Michael S. Gashler. 2018. “A parameterized activation function for learning fuzzy logic operations in deep neural networks.” In Systems, Man, and Cybernetics (SMC), 2017 IEEE International Conference on, 740-745. Banff, Canada: IEEE.
Godfrey, Luke B. and Michael S. Gashler. 2017. “Neural decomposition of time-series data.” In Systems, Man, and Cybernetics (SMC), 2017 IEEE International Conference on, 2796-2801. Banff, Canada: IEEE.
Godfrey, Luke B. and Michael S. Gashler. 2015. “A continuum among logarithmic, linear, and exponential functions, and its potential to improve generalization in neural networks.” In Knowledge Discovery, Knowledge Engineering and Knowledge Management (IC3K), 2015 7th International Joint Conference on, 481-486. Lisbon, Portugal: IEEE.