Brad McDanelAssistant Professor of Computer Science

Ph.D., Computer Science, Harvard University, 2019

M. Sc., Computer Science, Wake Forest University, 2012

B. Sc. Computer Science, Wake Forest University,  2010

My research spans the intersections of deep learning, hardware architecture, and computer networks, with a particular focus on developing efficient algorithms and systems for deploying artificial intelligence. I have extensive experience in optimizing deep neural networks (DNNs) through various approaches, including systolic array implementations, sparse architectures, and quantization techniques. My work has contributed to both theoretical frameworks and practical implementations for accelerating DNN inference on edge devices, especially in distributed network environments.

Recently I have expanded my research to address efficiency challenges in emerging AI systems, particularly Large Language Models (LLMs) and multi-modal architectures, as evidenced by my work on speculative decoding and transformer optimization techniques.  Learn More

See a complete list of publications at my Google Scholar Profile.

H. T. Kung, B. McDanel, S. Zhang. Term Revealing: Furthering Quantization at Run Time on Quantized DNNs. Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis (SC), 2020. (to appear)

B. McDanel, S. Zhang, H. T. Kung, X. Dong. Full-stack Optimization for Accelerating CNNs with FPGA Validation. 32nd ACM International Conference on Supercomputing (ICS), 2019.

H. T. Kung, B. McDanel, S. Zhang. Packing Sparse Convolutional Neural Networks for Efficient Systolic Array Implementations: Column Combining Under Joint Optimization. 24th ACM International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS), 2019.

S. Teerapittayanon,  B. McDanel, H. T. Kung. Distributed Deep Neural Networks over the Cloud, the Edge and End Devices. International Conference on Distributed Computing Systems (ICDCS), 2017.

B. McDanel, S. Teerapittayanon, H. T. Kung. Embedded Binarized Neural Networks. International Conference on Embedded Wireless Systems and Networks (EWSN), 2017.

S. Teerapittayanon, B. McDanel, H. T. Kung. BranchyNet: Fast Inference via Early Exiting from Deep Neural Networks. International Conference on Pattern Recognition (ICPR), 2016.