VolumetricCondensed

Christopher Clarke

DSP Software Developer (C++)

About Me

Graduated PhD in with research in Artificial Intelligence (DSP) from the Singapore University of Technology and Design (Science, Math, and Technology Cluster) – President’s Fellowship Program & Computer and Information Sciences (CIS) Scholarship. Member of the Interdisciplinary Audio and Acoustics Research Group at SUTD. My passion lies with low-latency audio plugin/framework implementations, particularly for applications that have traditionally been deemed otherwise. My PhD's research focuses on the AI/ML technologies to run extremely low-latency (microsecond and below) audio processing, even on low-compute devices such as embedded microcontrollers or System-on-a-Chip. As a Music Technologist with focus on generative algorithms and stochastic modelling for music generation, I have presented fixed site-specific installations and deployed software libraries on music generation

Sessions

  • Shrink Your VA Model Neural Networks!
    13:00 - 13:20 UTC | Friday 1st November 2024 | ADCx Gather
    Online Only

    Capturing the complex nonlinear behaviors of analog circuits in virtual analog modeling is a significant challenge. Selecting the appropriate neural network size and architecture for these function approximation tasks currently relies heavily on trial-and-error methods like grid search. These approaches are time-consuming, computationally intensive, and lack a solid theoretical foundation, often resulting in oversized models that are inefficient and impractical for real-time applications. This talk introduces ideas for a framework that systematically determines optimal neural network architectures for modeling. The talk will speak about examining the geometric structures and symmetries in the complexity of the model, and the designation of […]