通过模仿类脑认知和利用并行性，超维计算（HDC）分类器已经成为一个轻量级的框架，以实现有效的设备上的推理。尽管如此，它们有两个基本的缺点，启发式训练过程和超高的维度，这导致次优的推理精度和大的模型尺寸超出了具有严格资源约束的微小设备的能力。在本文中，我们解决这些根本的缺点，并提出了一个低维计算（LDC）的替代方案。具体来说，通过将我们的LDC分类器映射到等效的神经网络中，我们使用原则性训练方法优化了我们的模型。最重要的是，我们可以提高推理精度，同时成功地将现有HDC模型的超高维度降低了几个数量级（例如，8000 vs. 4/64）。我们运行实验来评估我们的LDC分类器，通过考虑不同的数据集在微小设备上进行推理，并在FPGA平台上实现不同的模型以进行加速。结果突出表明，我们的LDC分类器比现有的大脑启发的HDC模型具有压倒性的优势，特别适合在微型设备上进行推理。
英文摘要：
By mimicking brain-like cognition and exploiting parallelism, hyperdimensional computing (HDC) classifiers have been emerging as a lightweight framework to achieve efficient on-device inference. Nonetheless, they have two fundamental drawbacks, heuristic training process and ultra-high dimension, which result in sub-optimal inference accuracy and large model sizes beyond the capability of tiny devices with stringent resource constraints. In this paper, we address these fundamental drawbacks and propose a low-dimensional computing (LDC) alternative. Specifically, by mapping our LDC classifier into an equivalent neural network, we optimize our model using a principled training approach. Most importantly, we can improve the inference accuracy while successfully reducing the ultra-high dimension of existing HDC models by orders of magnitude (e.g., 8000 vs. 4/64). We run experiments to evaluate our LDC classifier by considering different datasets for inference on tiny devices, and also implement different models on an FPGA platform for acceleration. The results highlight that our LDC classifier offers an overwhelming advantage over the existing brain-inspired HDC models and is particularly suitable for inference on tiny devices.
Tiny noise, big mistakes: Adversarial perturbations induce errors in Brain-Computer Interface spellers
Huazhong University of Science and Technology（华中科技大学）；University of Technology Sydney（悉尼科技大学）；University of California San Diego（加州大学圣地亚哥分校）；Zürich University of Applied Sciences（苏黎世应用科技大学）
Tiny Brains, Giant Impact: Uncovering the Keystone Neurons of LLM with Just a Few Prompts
National University of Singapore（新加坡国立大学）；Beijing University of Posts and Telecommunications（北京邮电大学）；University of Science and Technology of China（中国科学技术大学）
Counterfactual Explanation of Brain Activity Classifiers using Image-to-Image Transfer by Generative Adversarial Network
Okayama University（冈山大学）；Japan Science and Technology Agency（日本科学技术振兴机构）；Rikkyo University（立教大学）；National Institute for Physiological Sciences（生理学研究所）；Araya Inc.（Araya 公司）；Keio University（庆应义塾大学）
Agreement Rate Initialized Maximum Likelihood Estimator for Ensemble Classifier Aggregation and Its Application in Brain-Computer Interface
DataNova；Human Research and Engineering Directorate, U.S. Army Research Laboratory（美国陆军研究实验室人类研究与工程局）；University of Texas at San Antonio（得克萨斯大学圣安东尼奥分校）；DCS Corp（DCS公司）；National Chiao-Tung University（国立交通大学）；University of Technology, Sydney（悉尼科技大学）
T2I-Diff: fMRI Signal Generation via Time-Frequency Image Transform and Classifier-Free Denoising Diffusion Models
School of Information Technology, Monash University Malaysia（莫纳什大学马来西亚分校信息科技学院）；Statistics Program, King Abdullah University of Science and Technology（国王阿卜杜勒阿齐兹大学科学与技术学院统计项目）
Adaptive neural network classifier for decoding MEG signals
Department of Neuroscience and Biomedical Engineering, Aalto University School of Science（阿尔托大学理学院神经科学与生物医学工程系）；Aalto NeuroImaging, Aalto University（阿尔托大学阿尔托神经成像中心）；Aalto University School of Science（阿尔托大学理学院）；Aalto University（阿尔托大学）
An EMG Gesture Recognition System with Flexible High-Density Sensors and Brain-Inspired High-Dimensional Classifier
Berkeley Wireless Research Center, EECS Department, University of California, Berkeley（加州大学伯克利分校电气工程与计算机科学系伯克利无线研究中心）；Integrated System Laboratory, ETH Zurich（苏黎世联邦理工学院集成系统实验室）；DEI, University of Bologna（博洛尼亚大学DEI（可能是Department of Electrical Engineering and Information Technology的缩写，常见译为电气工程与信息技术系））
Deep learning for spike detection in deep brain stimulation surgery
Department of Electronics and Information Technology, Warsaw University of Technology（华沙理工大学电子与信息技术系）；Research and Academic Computer Network (NASK-PIB)（研究与学术计算机网络（NASK-PIB））
An Automated Classifier of Harmful Brain Activities for Clinical Usage Based on a Vision-Inspired Pre-trained Framework
Medical School, Tianjin University（天津大学医学院）；Tianjin University（天津大学）；State Key Laboratory of Advanced Medical Materials and Devices, Tianjin University（天津大学先进医疗材料与设备国家重点实验室）；Haihe Laboratory of Brain-computer Interaction and Human-machine Integration, Tianjin（脑机交互与人机集成海河实验室）；Nell Hodgson Woodruff School of Nursing, Emory University（埃默里大学内尔·霍德森·伍德鲁夫护理学院）
Functional connectivity ensemble method to enhance BCI performance (FUCONE)
LISV, UVSQ, Université Paris-Saclay（巴黎萨克雷大学凡尔赛大学计算机科学实验室）；Sorbonne Université（索邦大学）；Institut du Cerveau - Paris Brain Institute - ICM（巴黎大脑研究所）；CNRS（法国国家科学研究中心）；Inria（法国国家信息与自动化研究所）；Inserm（法国国家健康与医学研究院）；AP-HP（巴黎公立医院集团）；Hôpital de la Pitié Salpêtrière（皮提耶-萨尔佩特里尔医院）；LAMSADE, PSL, Université Paris Dauphine（巴黎多芬大学巴黎文理研究大学决策数学应用实验室）
Triple Memory Networks: a Brain-Inspired Method for Continual Learning
Tsinghua-Peking Center for Life Sciences（清华-北大生命科学联合中心）；IDG/McGovern Institute for Brain Research（IDG/麦戈文脑科学研究院）；School of Life Sciences, Tsinghua University（清华大学生命科学学院）
Study on spike-and-wave detection in epileptic signals using t-location-scale distribution and the K-nearest neighbors classifier
Epilepsy and Telemetry Integral Center（癫痫与遥测综合中心）；Foundation for the Fight against Pediatric Neurological Disease (FLENI)（儿童神经疾病防治基金会（FLENI））；University of Toulouse（图卢兹大学）；IRIT-INP-ENSEEIHT（IRIT-INP-ENSEEIHT（法国国立应用科学学院图卢兹分院计算机科学、电子、电信与系统研究所））
