I am Co-Founder and CTO of LuxiTech , focusing on building brain-inspired large language models. These models are specifically designed to operate with high cognitive capabilities while consuming significantly less power compared to traditional LLMs.

I received the Ph.D degree from the Department of Electrical and Computer Engineering (ECE), University of California, Santa Cruz (UCSC). My research is co-supervised by Prof. Sung-Mo “Steve” Kang at Nanoelectronic Integrated Systems Laboratory and Prof. Jason Eshraghian at Neuromorphic Computing Group, and focuses on neuromorphic computing, spiking neural networks, and their hardware implementation using memristors.

My bachelor’s degree was received in 2016 from the Experimental Class of Qiming College, an independent college for the cultivation of top innovative students at Huazhong University of Science and Technology (HUST). Meanwhile, the degree is also awarded by the School of Artificial Intelligence and Automation (AIA) at HUST.

I also obtained working experience from Synsense, a neuromorphic startup that spun out of the Institute of Neuroinformatics at the University of Zurich and ETH Zurich; and Tetramem, a computing-in-memory startup whose RRAM technologies are based on Yang research group at USC, Nanodevices and Integrated Systems Laboratory at UMass Amherst, and HP labs.

I am passionate about developing an interdisciplinary approach to unraveling the mysteries of the brain and brain-inspired computing, spanning electrical and computer engineering, cognitive science, neuroscience, philosophy, etc. I am also a fan of basketball, skateboarding, snowboarding, ukulele, cats, Chinese calligraphy, and meditation. Feel free to reach out to me!

News

• [Jun. 13, 2024] My interview with STEM4ALL, supported by the United Nations Development Programme (UNDP) and the United Nations International Children’s Emergency Fund (UNICEF), is now available online!
• [Jun. 04, 2024] Paper “Scalable MatMul-free Language Modeling” is available in arXiv.
• [Apr. 08, 2024] Paper “Eagle and Finch: RWKV with matrix-valued states and dynamic recurrence” is available in arXiv.
• [Nov. 24, 2023] Paper “Neuromorphic intermediate representation: a unified instruction set for interoperable brain-inspired computing” is available in arXiv.
• [Oct. 13, 2023] Peng was invited to attend the United Nations event “The 2023 Policy Dialogue on Women in Science: Pathways towards Breaking Barriers in STEM”.
• [Oct. 08, 2023] Paper “RWKV: Reinventing RNNs for the Transformer Era” is accepted by 2023 EMNLP Findings!
• [May. 22, 2023] Paper “RWKV: Reinventing RNNs for the Transformer Era” is available in arXiv.
• [May. 22, 2023] Peng presented the paper “Backpropagating Errors Through Memristive Spiking Neural Networks” at the 2023 IEEE International Symposium on Circuits & Systems (IEEE ISCAS), Monterey, CA.
• [April. 29, 2023] The paper titled “How to Build a Memristive Integrate-and-Fire Neuron for Spiking Neuronal Signal Generation” has been awarded the 2023 IEEE Transaction on Circuits and Systems Darlington Best Paper Award. This paper was led by Prof. Sung-Mo Kang, Prof. Jason Eshraghian, and Prof. Leon O. Chua in a collaboration spanning UC Santa Cruz, UC Berkeley, University of Michigan, TU Dresden, and Syungkyunkwan University.
• [Feb. 22, 2023] “2023 Telluride Workshop on Neuromorphic Cognition Engineering” has been announced. Jason and I will be hosting one of the topic areas: Open-source neuromorphic hardware, software, and wetware.
• [Nov. 14, 2022] Paper “Gradient-based Neuromorphic Learning on Dynamical RRAM Arrays” is accepted by IEEE Journal on Emerging and Selected Topics in Circuits and Systems (IEEE JETCAS). It is a JETCAS special issue on Memristive Circuits and Systems for Edge-Computing Applications.
• [Sep. 13, 2022] Peng submitted a Spiking Neural Network Accelerator to tape-out in eFabless / Google SkyWater MPW7 shuttle.
• [Aug. 30, 2022] Congratulations to Prof. Jason Eshraghian for joining the ECE department as a new assistant professor. He leads the Neuromorphic Computing Group and co-advise Peng.
• [Jul. 15, 2022] Peng was awarded “Best New Neuromorph” during the 2022 Telluride Neuromorphic Workshop.
• [Jun. 26, 2022] Paper “Gradient-based Neuromorphic Learning on Dynamical RRAM Arrays” is available in arXiv.
• [Jun. 23, 2022] Peng gave a talk on “Memristive Spiking Neural Network for Neuromorphic Computing” at the Computer Science Department of Santa Clara University invited by Prof. Nam Ling and Prof. Tokunbo Ogunfunmi.
• [May. 31, 2022] Peng presented the paper “A Fully Memristive Spiking Neural Network with Unsupervised Learning” at the 2022 IEEE International Symposium on Circuits & Systems (IEEE ISCAS), Austin, TX.
• [Apr. 25, 2022] Peng has been selected to participate in the 2022 Telluride Workshop on Neuromorphic Cognition Engineering, which is the most famous neuromorphic workshop with a long history since the “neuromorphic” area originated.
• [Mar. 29, 2022] Peng has been selected as a 2022 Science Internship Program research mentor.
• [Mar. 02, 2022] Paper “SPICEprop: Backpropagating Errors Through Memristive Spiking Neural Networks” is available in arXiv.
• [Feb. 25, 2022] Patent “Splitting normalization method and device, audio feature extractor and chip” has been published.
• [Jan. 14, 2022] Paper “A Fully Memristive Spiking Neural Network with Unsupervised Learning” has been accepted at the 2022 IEEE International Symposium on Circuits & Systems (IEEE ISCAS).
• [Jan. 07, 2022] Patent “Pulse event decision device, method, chip and electronic equipment” has been published.
• [Nov. 18, 2021] Paper “How to Build a Memristive Integrate-and-Fire Model for Spiking Neuronal Signal Generation” has been published in: IEEE Transactions on Circuits and Systems–I: Regular Papers. We are honoured to have these international cooperations among Germany, Korea, the University of Michigan, UCB, and UCSC.
• [Oct. 23, 2021] Peng gave a talk on “Memristive Spiking Neural Network for Neuromorphic Computing” at the Integrated Circuit School, Huazhong University of Science and Technology.
• [May. 14, 2021] We received the Faculty Research Grant for “Bio-Inspired Memristive Spiking Neural Network for Machine Learning” research from the Committee on Research of the University of California, Santa Cruz.
• [Mar 30, 2021] Peng has been selected as a 2021 Science Internship Program research mentor.
• [Dec. 29, 2020] Paper “Automatically detecting bregma and lambda points in rodent skull anatomy images” has been published in: PloS one.
• [Sep. 14, 2020] Peng received the 2020 IEEE Nuclear Science Symposium and Medical Imaging Conference (IEEE NSS/MIC) trainee grant.
• [Jul. 29, 2020] Paper “Towards Real-Time Machine Learning for Anomaly Detection” has been accepted at the 2020 IEEE Nuclear Science Symposium and Medical Imaging Conference (IEEE NSS/MIC).
• [Mar. 16, 2019] Peng was accepted and graduated from the Graduate Student Leadership Certificate Program of the University of California, Santa Cruz.

Academic Services

• IEEE CASS Neural Systems and Applications (NSA) Technical Committee member
• IEEE CASS Cellular Nanoscale Networks and Memristor Array Computing (CNN-MAC) Technical Committee member

Conference Services

• Technical Program Committees member of 2024 3rd International Conference on Neuromorphic Computing (ICNC)
• Program Committee member of 2024 IEEE/ACM International Conference on Neuromorphic Systems (ICONS)
• Topic Leader of 2023 Telluride Neuromorphic Cognition Engineering Workshop

Journal Review

• IEEE Journal on Emerging and Selected Topics in Circuits and Systems
• IEEE Transactions on Circuits and Systems I: Regular Papers
• IEEE Transactions on Circuits and Systems II: Express Briefs
• IEEE Transactions on Biomedical Circuits and Systems
• Memetic Computing

Conference Review

• 2024 IEEE/ACM International Conference on Neuromorphic Systems (ICONS)
• 2024 IEEE Biomedical Circuits and Systems Conference (BIOCAS)
• 2023 IEEE Biomedical Circuits and Systems Conference (BIOCAS)
• 2023 IEEE International Symposium on Circuits & Systems (ISCAS)
• 2022 IEEE International Symposium on Circuits & Systems (ISCAS)
• 2022 IEEE International Midwest Symposium on Circuits and Systems (MWSCAS)
• 2021 IEEE International Midwest Symposium on Circuits and Systems (MWSCAS)

Teaching Assistant

• CSE 12: Computer Systems and Assembly Language and Lab, Spring 2022
• CSE 30: Programming Abstractions: Python, Winter 2022
• ECE 163: Introduction to Small-Scale UAV Theory and Practice, Spring 2021
• ECE 171: Analog Electronics, Winter 2021
• ECE 101: Introduction to Electronic Circuits, Fall 2020

Journal Paper

Neuromorphic intermediate representation: a unified instruction set for interoperable brain-inspired computing
Available in arXiv, Nov 2023.

Gradient-based Neuromorphic Learning on Dynamical RRAM Arrays
Peng Zhou, Donguk Choi, Wei D. Lu, Sung-Mo Kang, and Jason K. Eshraghian. IEEE Journal on Emerging and Selected Topics in Circuits and Systems, Nov 2022.

How to Build a Memristive Integrate-and-Fire Model for Spiking Neuronal Signal Generation
Sung Mo Kang, Donguk Choi, Jason K. Eshraghian, Peng Zhou, Jieun Kim, Bai Sun Kong, Xiaojian Zhu, Ahmet Samil Demirkol, Alon Ascoli, Ronald Tetzlaff, Wei D. Lu, and Leon O. Chua. IEEE Transactions on Circuits and Systems–I: Regular Papers, Nov 2021.

Automatically Detecting Bregma and Lambda Points in Rodent Skull Anatomy Images
Peng Zhou, Zheng Liu, Hemmings Wu, Yuli Wang, and Shiva Abbaszadeha. PLOS ONE, Dec 2020.

Biomimetic Spiking Neural Network based on Monolayer 2D Synapse with Short-Term Plasticity for Auditory Brainstem Processing
Jieun Kim, Peng Zhou, Unbok Wi, Bo-Min Joo, Donguk Choi, Myeong-Lok Seol, SravyamPulavarthi, Linfeng Sun, Heejun Yang, Woo-Jong You, Jin-Woo Han, Sung-Mo Kang, and Bai-Sun Kong. In preparation.

Conference Paper

Scalable MatMul-free Language Modeling
Available in arXiv, June 2024.

Eagle and finch: Rwkv with matrix-valued states and dynamic recurrence
Available in arXiv, June 2024.

Rwkv: Reinventing rnns for the transformer era
Empirical Methods in Natural Language Processing . EMNLP 2023.

Backpropagating Errors Through Memristive Spiking Neural Networks
IEEE International Symposium on Circuits and Systems. ISCAS 2023.

A Fully Memristive Spiking Neural Network with Unsupervised Learning
IEEE International Symposium on Circuits and Systems. ISCAS 2022.

Towards Real-Time Machine Learning for Anomaly Detection
IEEE Nuclear Science Symposium and Medical Imaging Conference. NSS/MIC 2020.

Open-source Framework

snnTorch: a Python package for trainig spiking neural networks, compatible with GPUs and Graphcore’s Intelligence Processing Units (IPUs).

Rockpool: a Python package for training spiking neural networks, compatible with GPUs and Synsense’s Xylo.

NIR: a set of computational primitives, shared across different neuromorphic frameworks and technology stacks. NIR is currently supported by 7 simulators and 4 hardware platforms, including Lava-DL, Nengo, Norse, Rockpool, Sinabs, snnTorch, SpiNNaker2, Spyx, Speck, Xylo, etc, allowing users to seamlessly move between any of these platforms.

Open-source Chip

Spiking Neural Network Accelerator: Binarized spiking neural network ASIC with adaptive threshold and recurrent connections.

Patent

CN/WO/US: Pulse event decision device, method, chip and electronic equipment
Peng Zhou, Yannan Xing, Ning Qiao, Yudi Ren, Zheng Ke, Yanlun Hu, Bo Li, Yuhang Liu, Xiwen Gong, Sadique Sheik, Dylan Richard Muir.

CN/WO/US: Splitting normalization method and device, audio feature extractor and chip
Huaqiu Zhang, Dylan Richard Muir, Saeid Haghighatshoar, Hao Liu, Peng Zhou, Ning Qiao.