arXiv subjects

Jason Christopher

Publications and source records attributed to Jason Christopher.

3 recordsLinked to original sources

arXiv2026

FRESH: Information-Geometric Calibration of Patient-Level Models to Aggregate Evidence

This note introduces FRESH (Fusion of Recent Evidence and Subject Histories), a method for incorporating population-level summary results -- published clinical trials, registry summaries, prior natural-history studies, and peer-reviewed indirect comparisons -- into predictive models trained on patient-level data. This method provides a principled means of combining both patient-level and aggregate-level data types into a unified data-efficient model for clinical decision making. FRESH assumes access to a generative model trained on patient-level data sources (e.g. clinical trial or real-world data). The method produces patient-level predictions from a re-calibrated model that matches a set of specified aggregate statistics for a target population. This can be understood as a patient-level recapitulation of the aggregate source -- with the key property that the recalibration is a minimal perturbation of the original joint distribution in a specific information-geometric sense. The resulting samples can be analyzed directly or combined into a post-training procedure to update the original generative model. This approach enables several applications where rigorously incorporating patient-level data with summary information is valuable, including (i) contextualizing single-arm trial results with respect to recent standard-of-care, (ii) clinical-trial simulations for design and probability-of-technical-success estimation, and (iii) comparative-effectiveness analyses of on-market therapies.

stat.ME↗

arXiv2024

Self-Driving Car Racing: Application of Deep Reinforcement Learning

This paper explores the application of deep reinforcement learning (RL) techniques in the domain of autonomous self-driving car racing. Motivated by the rise of AI-driven mobility and autonomous racing events, the project aims to develop an AI agent that efficiently drives a simulated car in the OpenAI Gymnasium CarRacing environment. We investigate various RL algorithms, including Deep Q-Network (DQN), Proximal Policy Optimization (PPO), and novel adaptations that incorporate transfer learning and recurrent neural networks (RNNs) for enhanced performance. The project demonstrates that while DQN provides a strong baseline for policy learning, integrating ResNet and LSTM models significantly improves the agent's ability to capture complex spatial and temporal dynamics. PPO, particularly in continuous action spaces, shows promising results for fine control, although challenges such as policy collapse remain. We compare the performance of these approaches and outline future research directions focused on improving computational efficiency and addressing model stability. Our findings contribute to the ongoing development of AI systems in autonomous driving and related control tasks.

cs.AI↗

arXiv2016

Wireless transfer of power by a 35-GHz metamaterial split-ring resonator rectenna

Wireless transfer of power via high frequency microwave radiation using a miniature split ring resonator rectenna is reported. RF power is converted into DC power by integrating a rectification circuit with the split ring resonator. The near-field behavior of the rectenna is investigated with microwave radiation in the frequency range between 20-40 GHz with a maximum power level of 17 dBm. The observed resonance peaks match those predicted by simulation. Polarization studies show the expected maximum in signal when the electric field is polarized along the edge of the split ring resonator with the gap and minimum for perpendicular orientation. The efficiency of the rectenna is on the order of 1% for a frequency of 37.2 GHz. By using a cascading array of 9 split ring resonators the output power was increased by a factor of 20.

physics.ins-det↗