Kangjun Bai

Kangjun Bai

Auto-generated profile, based on publicly available information

Kangjun Bai

Air Force Research Lab. (United States)

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
11 October 2019 in IEEE Transactions on Very Large Scale Integration (VLSI) Systems
Verified
Journal Article
Closed access
KBKangjun Bai
Kangjun Bai
QAQiyuan An
Qiyuan An
LLLingjia Liu
Lingjia Liu
Yang (Cindy) YiYang (Cindy) Yi
Yang (Cindy) Yi

1 January 2023 in IEEE Circuits and Systems Magazine
Verified
Journal Article
Closed access
KBKang Jun Bai
Kang Jun Bai
CTClare Thiem
Clare Thiem
JLJack Lombardi
Jack Lombardi
YLYibin Liang
Yibin Liang
Yang (Cindy) YiYang (Cindy) Yi
Yang (Cindy) Yi
Reservoir computing (RC) is a neural computing paradigm especially well-suited for learning dynamical systems by leveraging an untrained reservoir layer, providing high-dimensional input encoding with fading memory property. Since only the readout weights are trained under RC, linear regression learning algorithms are sufficient, leading to significant improvements in computational complexity and energy efficiency as compared to other deep neural networks (DNNs). RC offers an alternative solution to sidestep the shortcomings of data scarcity and the vanishing gradient problem. More importantly, such a network structure is amenable to hardware implementation using a variety of devices, circuits, and systems, making RC a good candidate to replace sophisticated DNNs as a lightweight classifier at the edge for internet of things (IoT) applications. In this article, we provide an overview of recent advances in RC hardware and their applications for mobile edge intelligence. Specifically, we will demonstrate the design strategies of RC in opto-electronic configuration, fully digital system, and silicon with the mixed-signal integrated circuit approach. Moreover, we will expose a novel implementation approach using emerging materials, designing the way for RC to be used in the next-generation neuromorphic computing systems. Building upon these efficient RC models, their applicability and effectiveness against the state-of-the-art are then demonstrated through diverse machine learning benchmarks spanning the area of IoT, communication networks, and healthcare.

16 April 2021 in IEEE Transactions on Circuits and Systems I: Regular Papers
Verified
Journal Article
Closed access
KBKangjun Bai
Kangjun Bai
LLLingjia Liu
Lingjia Liu
Yang (Cindy) YiYang (Cindy) Yi
Yang (Cindy) Yi
Deep learning (DL) has gained unprecedented success in many real-world applications. However, DL poses difficulties for efficient hardware implementation due to the needs of a complex gradient-based learning algorithm and the required high memory bandwidth for synaptic weight storage, especially in today's data-intensive environment. Computing-in-memory (CIM) strategies have emerged as an alternative for realizing energy-efficient neuromorphic applications in silicon, reducing resources and energy required for neural computations. In this work, we exploit a CIM-based spatial-temporal hybrid neural network (STHNN) with a unique learning algorithm. To be specific, we integrate both multilayer perceptron and recurrent-based delay-dynamical system, making the network becomes linear separable while processing information in both spatial and temporal domains, better yet, reducing the memory bandwidth and hardware overhead through the CIM architecture. The prototype fabricated in 180 nm CMOS process is built of fully-analog components, yielding an average on-chip classification accuracy up to 86.9% on handprinted alphabet characters with a power consumption of 33 mW. Beyond that, through the handwritten digit database and the radio frequency fingerprinting dataset, software-based numerical evaluations offer 1.6 -to- 9.8 × and 1.9 -to- 4.4 × speedup, respectively, without significantly degrading its classification accuracy compared to the cutting-edge DL approaches.

4 May 2020 in IEEE Journal on Emerging and Selected Topics in Circuits and Systems
Verified
Journal Article
Closed access
KBKangjun Bai
Kangjun Bai
Yang (Cindy) YiYang (Cindy) Yi
Yang (Cindy) Yi
ZZZhou Zhou
Zhou Zhou
SJShashank Jere
Shashank Jere
LLLingjia Liu
Lingjia Liu

3 October 2018
Verified
Book Chapter
Open access
PDF file
HAHongyu An
Hongyu An
KBKangjun Bai
Kangjun Bai
Yang (Cindy) YiYang (Cindy) Yi
Yang (Cindy) Yi
Neuromorphic computing, an emerging non-von Neumann computing mimicking the physical structure and signal processing technique of mammalian brains, potentially achieves the same level of computing and power efficiencies of mammalian brains. This chapter will discuss the state-of-the-art research trend on neuromorphic computing with memristors as electronic synapses. Furthermore, a novel three-dimensional (3D) neuromorphic computing architecture combining memristor and monolithic 3D integration technology would be introduced; such computing architecture has capabilities to reduce the system power consumption, provide high connectivity, resolve the routing congestion issues, and offer the massively parallel data processing. Moreover, the design methodology of applying the capacitance formed by the through-silicon vias (TSVs) to generate a membrane potential in 3D neuromorphic computing system would be discussed in this chapter.

19 January 2023 in IEEE Transactions on Very Large Scale Integration (VLSI) Systems
Verified
Journal Article
Closed access
HZHonghao Zheng
Honghao Zheng
KBKang Jun Bai
Kang Jun Bai
Yang (Cindy) YiYang (Cindy) Yi
Yang (Cindy) Yi
From rate to temporal encoding, spiking information processing has demonstrated advantages across diverse neuromorphic applications. In the aspects of data capacity and robustness, multiplexing encoding outperforms alternative encoding schemes. In this work, we aim to implement a new class of multiplexing temporal encoders, patterning stimuli in multiple timescales to improve the information processing capability, and robustness of systems deployed in noisy environments. Benefitted by the internal reference frame using subthreshold membrane oscillation (SMO), the encoded spike patterns are less sensitive to the input noise, increasing the encoder’s robustness. Our design results in a tremendous saving on power consumption and silicon area compared with the power-hungry analog-to-digital converters. Furthermore, a working prototype of the multiplexing temporal encoder built based on an interspike interval (ISI) encoding scheme is implemented on a silicon chip using the standard 180-nm CMOS process. To the best of our knowledge, our introduced encoder demonstrates the first integrated circuit (IC) implementation of neural encoding with multiplexing topology. Finally, the accuracy and efficiency of our design are evaluated through standard machine learning benchmarks, including Modified National Institute of Standards and Technology (MNIST), Canadian Institute For Advanced Research (CIFAR)-10, Street View House Number (SVHN), and spectrum sensing in high-speed communication networks. While our multiplexing temporal encoder demonstrates a higher classification accuracy across all the benchmarks, the power consumption and dissipated energy per spike reach merely $2.6~\mu \text {W}$ and 95 fJ/spike, respectively, with an effective frame rate of 300 MHz. Compared with alternative encoding schemes, our multiplexing temporal encoder achieves at most 100% higher data capacity, 11.4% more accurate in classification, and 25% more robust against noise. Compared with the state-of-the-art designs, our work achieves up to $105 \times $ power efficiency without significantly increasing the silicon area.