The research presented in this Honors Thesis provides development in machine learning models which predict future states of a system with unknown dynamics, based on observations of the system. Two case studies are presented for (1) a non-conservative pendulum and (2) a differential game dictating a two-car uncontrolled intersection scenario. In the paper we investigate how learning architectures can be manipulated for problem specific geometry. The result of this research provides that these problem specific models are valuable for accurate learning and predicting the dynamics of physics systems.<br/><br/>In order to properly model the physics of a real pendulum, modifications were made to a prior architecture which was sufficient in modeling an ideal pendulum. The necessary modifications to the previous network [13] were problem specific and not transferrable to all other non-conservative physics scenarios. The modified architecture successfully models real pendulum dynamics. This case study provides a basis for future research in augmenting the symplectic gradient of a Hamiltonian energy function to provide a generalized, non-conservative physics model.<br/><br/>A problem specific architecture was also utilized to create an accurate model for the two-car intersection case. The Costate Network proved to be an improvement from the previously used Value Network [17]. Note that this comparison is applied lightly due to slight implementation differences. The development of the Costate Network provides a basis for using characteristics to decompose functions and create a simplified learning problem.<br/><br/>This paper is successful in creating new opportunities to develop physics models, in which the sample cases should be used as a guide for modeling other real and pseudo physics. Although the focused models in this paper are not generalizable, it is important to note that these cases provide direction for future research.

This research endeavor explores the 1964 reasoning of Irish physicist John Bell and how it pertains to the provoking Einstein-Podolsky-Rosen Paradox. It is necessary to establish the machinations of formalisms ranging from conservation laws to quantum mechanical principles. The notion that locality is unable to be reconciled with the quantum paradigm is upheld through analysis and the subsequent Aspect experiments in the years 1980-1982. No matter the complexity, any local hidden variable theory is incompatible with the formulation of standard quantum mechanics. A number of strikingly ambiguous and abstract concepts are addressed in this pursuit to deduce quantum's validity, including separability and reality. `Elements of reality' characteristic of unique spaces are defined using basis terminology and logic from EPR. The discussion draws directly from Bell's succinct 1964 Physics 1 paper as well as numerous other useful sources. The fundamental principle and insight gleaned is that quantum physics is indeed nonlocal; the door into its metaphysical and philosophical implications has long since been opened. Yet the nexus of information pertaining to Bell's inequality and EPR logic does nothing but assert the impeccable success of quantum physics' ability to describe nature.

Treatment log files for spot scanning proton therapy provide a record of delivery accuracy, but they also contain diagnostic information for machine performance. A collection of patient log files can identify machine performance trends over time. This facilitates the identification of machine issues before they cause downtime or degrade treatment quality. At Mayo Clinic Arizona, all patient treatment logs are stored in a database. These log files contain information including the gantry, beam position, monitor units (MUs), and gantry angle. This data was analyzed to identify trends, which were then correlated with quality assurance measurements and maintenance records.