Qian Zhang

Qian Zhang

Auto-generated profile, based on publicly available information

Qian Zhang

BrainCog Lab, Institute of Automation, Chinese Academy of Sciences, Beijing, China

Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

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

Representative Publications

View All Publications
5 June 2023 in IEEE Transactions on Very Large Scale Integration (VLSI) Systems
Verified
Journal Article
Open access
JLJindong Li
Jindong Li
GSGuobin Shen
Guobin Shen
DZDongcheng Zhao
Dongcheng Zhao
QZQian Zhang
Qian Zhang
YZYi Zeng
Yi Zeng
Spiking neural networks (SNNs) have been widely used due to their strong biological interpretability and high-energy efficiency. With the introduction of the backpropagation algorithm and surrogate gradient, the structure of SNNs has become more complex, and the performance gap with artificial neural networks (ANNs) has gradually decreased. However, most SNN hardware implementations for field-programmable gate arrays (FPGAs) cannot meet arithmetic or memory efficiency requirements, which significantly restricts the development of SNNs. They do not delve into the arithmetic operations between the binary spikes and synaptic weights or assume unlimited on-chip RAM resources using overly expensive devices on small tasks. To improve arithmetic efficiency, we analyze the neural dynamics of spiking neurons, generalize the SNN arithmetic operation to the multiplex-accumulate operation, and propose a high-performance implementation of such operation by utilizing the DSP48E2 hard block in Xilinx Ultrascale FPGAs. To improve memory efficiency, we design a memory system to enable efficient synaptic weights and membrane voltage memory access with reasonable on-chip RAM consumption. Combining the above two improvements, we propose an FPGA accelerator that can process spikes generated by the firing neurons on-the-fly (FireFly). FireFly is the first SNN accelerator that incorporates DSP optimization techniques into SNN synaptic operations. FireFly is implemented on several FPGA edge devices with limited resources but still guarantees a peak performance of 5.53 TOP/s at 300 MHz. As a lightweight accelerator, FireFly achieves the highest computational density efficiency compared with existing research using large FPGA devices.

25 March 2024 in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
Verified
Journal Article
Closed access
JLJindong Li
Jindong Li
GSGuobin Shen
Guobin Shen
DZDongcheng Zhao
Dongcheng Zhao
QZQian Zhang
Qian Zhang
YZYi Zeng
Yi Zeng
Spiking neural networks (SNNs) are expected to be a promising alternative to artificial neural networks (ANNs) due to their strong biological interpretability and high energy efficiency. Specialized SNN hardware offers clear advantages over general-purpose devices in terms of power and performance. However, there is still room to advance hardware support for state-of-the-art (SOTA) SNN algorithms and improve computation and memory efficiency. As a further step in supporting high-performance SNNs on specialized hardware, we introduce FireFly v2, an field-programmable gate array (FPGA) SNN accelerator that can address the issue of nonspike operation in current SOTA SNN algorithms, which presents an obstacle in the end-to-end deployment onto existing SNN hardware. To more effectively align with the SNN characteristics, we design a spatiotemporal dataflow that allows four dimensions of parallelism and eliminates the need for membrane potential storage, enabling on-the-fly spike processing and spike generation. To further improve hardware acceleration performance, we develop a high-performance spike computing engine as a backend based on a systolic array operating at 500–600 MHz. To the best of our knowledge, FireFly v2 achieves the highest clock frequency among all FPGA-based implementations. Furthermore, it stands as the first SNN accelerator capable of supporting nonspike operations, which are commonly used in advanced SNN algorithms. FireFly v2 has doubled the throughput and DSP efficiency when compared to our previous version of FireFly and it exhibits $\times 1.33$ the DSP efficiency and $\times 1.42$ the power efficiency compared to the current most advanced FPGA accelerators.

1 August 2019
Verified
Conference Paper
Closed access
SFShuang Fang
Shuang Fang
XMXianghua Ma
Xianghua Ma
YZYang Zhao
Yang Zhao
QZQian Zhang
Qian Zhang
YLYaoyao Li
Yaoyao Li
Trajectory planning ensures that the robot arm moves smoothly and quickly to the target position. The difficulty is to use inverse kinematics to convert the path point into the joint angle and fit a smooth function to each joint. This paper studies the polynomial trajectory planning of the seven-DOF cooperative robot KUKA LBR iiwa. Kinematics of robot arm is analyzed in the coordinate system established by denavit-hartenberg method. In the joint space, the trajectory planning of the robot arm is performed using the cubic polynomial and the quintic polynomial function. The simulation results show that the quintic polynomial method effectively solves the problem of acceleration discontinuity, and obtains a continuous smooth trajectory curve of each joint, which visually verifies the effect of trajectory planning and provides an efficient and feasible trajectory planning method.

9 September 2021 in Frontiers in Systems Neuroscience
Verified
Journal Article
Open access
QZQian Zhang
Qian Zhang
YZYi Zeng
Yi Zeng
TZTielin Zhang
Tielin Zhang
TYTaoyi Yang
Taoyi Yang
Elucidating the multi-scale detailed differences between the human brain and other brains will help shed light on what makes us unique as a species. Computational models help link biochemical and anatomical properties to cognitive functions and predict key properties of the cortex. Here, we present a detailed human neocortex network, with all human neuron parameters derived from the newest Allen Brain human brain cell database. Compared with that of rodents, the human neural network maintains more complete and accurate information under the same graphic input. Unique membrane properties in human neocortical neurons enhance the human brain’s capacity for signal processing.

1 July 2016 in Chinese Science Bulletin
Verified
Journal Article
Open access
QZQian Zhang
Qian Zhang
YDYanhui Dong
Yanhui Dong
STShaoQing TONG
ShaoQing TONG
XLXiao Li
Xiao Li
LWLiHeng WANG
LiHeng WANG

15 November 2024 in IEEE Transactions on Circuits and Systems I: Regular Papers
Verified
Journal Article
Closed access
TLTenglong Li
Tenglong Li
JLJindong Li
Jindong Li
GSGuobin Shen
Guobin Shen
DZDongcheng Zhao
Dongcheng Zhao
QZQian Zhang
Qian Zhang
YZYi Zeng
Yi Zeng
Spiking Neural Networks (SNNs), with their brain-inspired structure using discrete spikes instead of continuous activations, are gaining attention for their potential of efficient processing on neuromorphic chips. While current SNN hardware accelerators often prioritize temporal spike sparsity, exploiting sparse synaptic weights offers significant untapped potential for even greater efficiency. To address this, we propose FireFly-S, a Sparse extension of the FireFly series. This co-optimized software-hardware design focusing on leveraging dual-side sparsity for acceleration. On the software side, we propose a novel algorithmic optimization framework that combines gradient rewiring for pruning and modified Learned Step Size Quantization (LSQ) tailored for SNNs, which achieves remarkable weight sparsity exceeding 85% and enables efficient 4-bit quantization with negligible accuracy loss. On the hardware side, we present an efficient dual-side sparsity detector employing a Bitmap-based sparse decoding logic to pinpoint the positions of non-zero weights and input spikes. The logic allows for the direct bypassing of redundant computations, thereby enhancing computational efficiency. Different from the overlay architecture adopted by previous FireFly series, we adopt a parametric spatial architecture with inter-layer pipelining that can fully exploit the fine-grained programmability and reconfigurability of Field-Programmable Gate Arrays (FPGAs), enabling fast deployment for various models. A spatial-temporal dataflow is also proposed to support such inter-layer pipelining and avoid long-term temporal dependencies. In experiments conducted on the MNIST, DVS-Gesture and CIFAR-10 datasets, the FireFly-S model achieves 85-95% sparsity with 4-bit quantization and the hardware accelerator effectively leverages the dual-side sparsity, delivering outstanding performance metrics of 10,047 FPS/W on MNIST, 3,683 FPS/W on DVS-Gesture, and 2,327 FPS/W on CIFAR-10.