Dr. Jacob Hochhalter
“Machine Learning in Engineering and Science” Mechanical Engineering, University of Utah; NASABiographical Info
Dr. Hochhalter joined the University of Utah (UU) as an Assistant Professor of Mechanical Engineering in 2018. At the same time, he began the Materials Prognosis from Integrated Modeling & Experiment (M’) Lab, which researches emergent structural and material prognosis issues that involve the multiscale and stochastic nature of plasticity and fatigue cracking. He also currently works as a senior engineer at Analytical Services and Materials and serves on the NASA Engineering and Safety Center (NESC) Materials TDT. Prior to joining UU, he was a Materials Research Engineer and group lead for the Damage Science Group in the Durability and Damage Tolerance Branch at NASA Langley Research Center. Through involvement with NASA, Dr. Hochhalter has received the NESC Engineering Excellence Award and NASA Early Career Achievement Medal. He was supported as a Cornell University Ph.D. student by a NASA Graduate Student Research Fellowship, where he graduated in 2010 with a dissertation topic on computational methods development for simulating the stages of microstructurally-small fatigue crack growth in Aluminum alloys.
Jake talked about his research and engineering experiences at NASA and as a professor of Mechanical Engineering. We discussed machine learning applications in the context of our everyday experiences and some important aspects that arise in their application to engineering and science. Then, we completed the classical falling-ball experiment, initially used by Galileo to study object trajectory. We acquired data, observed variability, and discussed model formulations both from the context of Galileo’s time and the modern machine learning approach.