Mentor: Lalitha Sankar
Alpha-loss is a tunable loss function with a parameter alpha that bridges log-loss for (alpha = 1) and 0-1 loss for (alpha = infinity). In machine learning literature, the theoretically optimal loss function is the 0-1 loss function. Unfortunately, 0-1 loss is computationally intractable due to being non-differentiable and discontinuous. Thus, it will be extremely beneficial to continue exploring such a surrogate loss function and how well it can emulate 0-1 loss. Discovering such desirable properties of this loss function will provide engineers and machine learning enthusiast better performance and more variability in neural network designs.
Perovskite Surface Analysis
Mentor: Zachary Holman
The primary objective of this research is to eliminate optical loses in perovskite silicon tandem solar cells. To understand the characteristics of the solar cell, the research required an accurate surface analysis of the thin films used. To do such, atomic force microscopy (AFM) was conducted using a scanning probe microscope. AFM uses a probe that physically taps the surface of a sample while collecting data to form images at the atomic level. In the future, other capabilities of the scanning probe microscope will be applied for further analysis.