Search Results - paul+bogdan

5 Results Sort By:

2022-051 - Multiwavelet-Based Operator Learning for Differential Equations

Physical modeling, including aerospace and complex fluid flow Biological modeling, including bacterial dynamics and neuron potential Epidemiology Abstract USC researchers introduce a novel method to solve partial differential equations (PDEs) using a multiwavelet-based neural operator learning scheme. By compressing the operator's kernel using...

Published: 2/3/2026 Inventor(s): Paul Bogdan, Gaurav Gupta, Xiong Ye Xiao
Keywords(s):  

2018-131 - Providing Higher Performance and Energy Efficiency with Processing-in-Memory (PIM)

Big data analytics Abstract USC researchers have developed an optimization technique that finds the best data location scheme for PIM systems. This technique improves both performance and energy consumption. Experimental results demonstrate that this technique improves system performance by 9.8x and achieves a 2.3x energy reductions, compared to...

Published: 12/12/2025 Inventor(s): Paul Bogdan, Shahin Nazarian, Yao Xiao
Keywords(s):  

2024-105 - GAHLS: AI-Guided High-Level Synthesis for Automated FPGA/ASIC Accelerator Generation

Market Opportunity There is a growing need for high-performance, low-latency, and energy-efficient hardware in autonomous systems, robotics, brain-machine interfaces, edge AI, and cyber-physical systems. Existing HLS tools often fail to efficiently exploit parallelism, optimize memory bandwidth, or generate domain-specific accelerator architectures...

Published: 2/3/2026 Inventor(s): Paul Bogdan, Shahin Nazarian, Yao Xiao
Keywords(s):  

2020-190 - Using Machine Learning to Predict Drug Properties

Drug discovery Antibacterial resistance Treatment of life-threatening and rare diseases Abstract USC researchers have developed a machine learning approach that can infer drug properties from known information about drug-target interactions. The technique is used to build a weighted Drug-Drug Similarity Network that can generate drug communities...

2022-169 -Epilepsy Mitigation with Stabilizing Linear Fractional-Order Dynamical Networks

Epilepsy treatment Abstract USC researchers propose a method to stabilize linear fractional-order systems using linear matrix inequalities. The approach addresses the challenge of stability in these systems and offers insights into mitigating epilepsy. The main contributions of this work include providing tractable conditions for the global asymptotic...

Published: 2/3/2026 Inventor(s): Paul Bogdan, Emily Reed, Sergio Pequito, Guilherme Ramos
Keywords(s):