Garv Shah
Pronouns: he/him
Research Mentor(s): Johannes Lange
Research Mentor School/College/Department: Physics / LSA
Program: UROPF
Session: Session 2 (10:00am – 10:50am)
Authors: Garv Shah, Johannes Lange
Abstract
This projects aims at improving the accuracy of artificial neural networks used as part of a larger algorithm for Bayesian posterior and evidence estimation. Different neural network architectures were implemented using the TensorFlow framework. Among others, we test how the predictive performance depends on the number of neurons and the activation function. The results are compared with the neural network architecture currently implemented in the codebase using the scikit-learn package.
