Biophysically detailed neuron simulation is a powerful tool to explore the mechanisms behind biological experiments and bridge the gap between various scales in neuroscience research. However, the extremely high computational complexity of detailed neuron simulation restricts the modeling and exploration of detailed network models. The bottleneck is solving the system of linear equations. To accelerate detailed simulation, we propose a heuristic tree-partition-based parallel method (HTP) to parallelize the computation of the Hines algorithm, the kernel for solving linear equations, and leverage the strong parallel capability of the graphic processing unit (GPU) to achieve further speedup. We formulate the problem of how to get a fine parallel process as a tree-partition problem. Next, we present a heuristic partition algorithm to obtain an effective partition to efficiently parallelize the equation-solving process in detailed simulation. With further optimization on GPU, our HTP method achieves 2.2 to 8.5 folds speedup compared to the state-of-the-art GPU method and 36 to 660 folds speedup compared to the typical Hines algorithm.

Ultra-high-speed object detection and tracking are crucial in fields such as fault detection and scientific observation. Existing solutions to this task have deficiencies in processing speeds. To deal with this difficulty, we propose a neural-inspired ultra-high-speed moving object filtering, detection, and tracking scheme, as well as a corresponding accelerator based on a high-speed spike camera. We parallelize the filtering module and divide the detection module to accelerate the algorithm and balance latency among modules for the benefit of the task-level pipeline. To be specific, a block-based parallel computation model is proposed to accelerate the filtering module, and the detection module is accelerated by a parallel connected component labeling algorithm modeling spike sparsity and spatial connectivity of moving objects with a searching tree. The hardware optimizations include processing the LIF layer with a group of multiplexers to reduce ADD operations and replacing expensive exponential operations with multiplications of preprocessed fixed-point values to increase processing speed and minimize resource consumption. We design an accelerator with the above techniques, achieving 19 times acceleration over the serial version after 25-way parallelization. A processing system for the accelerator is also implemented on the Xilinx ZCU-102 board to validate its functionality and performance. Our accelerator can process more than 20,000 spike images with 250 × 400 resolution per second with 1.618 W dynamic power consumption.

Images of visual scenes comprise essential features important for visual cognition of the brain. The complexity of visual features lies at different levels, from simple artificial patterns to natural images with different scenes. It has been a focus of using stimulus images to predict neural responses. However, it remains unclear how to extract features from neuronal responses. Here we address this question by leveraging two-photon calcium neural data recorded from the visual cortex of awake macaque monkeys. With stimuli including various categories of artificial patterns and diverse scenes of natural images, we employed a deep neural network decoder inspired by image segmentation technique. Consistent with the notation of sparse coding for natural images, a few neurons with stronger responses dominated the decoding performance, whereas decoding of ar tificial patterns needs a large number of neurons. When natural images using the model pretrained on artificial patterns are decoded, salient features of natural scenes can be extracted, as well as the conventional category information. Altogether, our results give a new perspective on studying neural encoding principles using reverse-engineering decoding strategies.