Article
Chemistry, Multidisciplinary
Joon-Kyu Han, Sang-Chan Park, Ji-Man Yu, Jae-Hyuk Ahn, Yang-Kyu Choi
Summary: The study demonstrates a novel biomimicked neuromorphic sensor for an electronic tongue, which can simultaneously detect ion concentrations and encode spike signals to mimic biological neurons in a neural network. pH-sensitive and sodium-sensitive artificial gustatory neurons are implemented using different sensing materials, and a sensitivity control inspired by biological sensory neurons is demonstrated.
Article
Engineering, Electrical & Electronic
Md Munir Hasan, Jeremy Holleman
Summary: This paper presents a simulation method for spiking neural networks that takes into account the non-idealities of hardware devices, as an alternative to time-consuming circuit simulations. By using the phase plane of the dynamical system, the proposed method captures the device non-idealities and enables simulation of spiking neural networks.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS II-EXPRESS BRIEFS
(2023)
Article
Computer Science, Artificial Intelligence
Susanna Gordleeva, Yuliya A. Tsybina, Mikhail I. Krivonosov, Ivan Y. Tyukin, Victor B. Kazantsev, Alexey Zaikin, Alexander N. Gorban
Summary: Mammalian brains can react quickly and effectively to danger due to their ability to recognize patterns. This study proposes a neuron-astrocyte network topology that is adapted to accommodate situation-based memory. Numerical simulations show that astrocytes are necessary for effective function in such a learning and testing set-up. The results also demonstrate that a neuromorphic computational model with astrocyte-induced modulation enhances retrieval quality compared to standard neural networks.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Man Yao, Guangshe Zhao, Hengyu Zhang, Yifan Hu, Lei Deng, Yonghong Tian, Bo Xu, Guoqi Li
Summary: This paper studies the application of attention mechanisms in brain-inspired spiking neural networks (SNNs). By optimizing the membrane potentials using a multi-dimensional attention module, the performance and energy efficiency of SNNs are improved. Experimental results demonstrate that SNNs with attention achieve better performance and sparser spiking firing in event-based action recognition and image classification tasks. The effectiveness of attention SNNs is theoretically proven and further analyzed using a proposed spiking response visualization method. This work highlights the potential of SNNs as a general backbone for various applications in the field of SNN research.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2023)
Article
Neurosciences
Dongwoo Lew, Hoyoung Tang, Jongsun Park
Summary: This paper proposes an input-dependent computation reduction approach by pruning relatively unimportant neurons in order to reduce computational complexity while maintaining high accuracy. The proposed neuron pruning scheme achieves significant energy reduction and speed up with acceptable accuracy loss.
FRONTIERS IN NEUROSCIENCE
(2023)
Article
Chemistry, Analytical
Fraser L. A. Macdonald, Nathan F. Lepora, Jorg Conradt, Benjamin Ward-Cherrier
Summary: This study investigates neuromorphic tactile sensation for edge orientation detection using an event-based optical tactile sensor combined with spiking neural networks.
Article
Neurosciences
Beck Strohmer, Rasmus Karnoe Stagsted, Poramate Manoonpong, Leon Bonde Larsen
Summary: Researchers have historically focused on two types of neurons in neural networks: non-spiking neurons for computer implementation and spiking neurons requiring special hardware, but new research shows that a combination of spiking and non-spiking neurons can create a sensorimotor pathway capable of shaping network output based on analog input, potentially improving locomotion strategies of legged robots.
FRONTIERS IN NEUROSCIENCE
(2021)
Article
Engineering, Biomedical
S. G. Hu, G. C. Qiao, X. K. Liu, Y. H. Liu, C. M. Zhang, Yue Zuo, Pujun Zhou, Y. A. Liu, Ning Ning, Qi Yu, Yang Liu
Summary: This study proposes a co-designed neuromorphic core based on quantized spiking neural network technology, which offers a new solution to improve neuron integration efficiency and effectively reduces the pressure on core area caused by increasing neuron numbers.
IEEE TRANSACTIONS ON BIOMEDICAL CIRCUITS AND SYSTEMS
(2022)
Article
Chemistry, Multidisciplinary
Joon-Kyu Han, Mingu Kang, Jaeseok Jeong, Incheol Cho, Ji-Man Yu, Kuk-Jin Yoon, Inkyu Park, Yang-Kyu Choi
Summary: A neuromorphic module of an electronic nose is demonstrated using a chemoresistive gas sensor and a single transistor neuron. It simultaneously detects gases and encodes spike signals, mimicking the biological olfactory system. An analysis of the mixed signals using a spiking neural network allows the identification of odor sources. This approach eliminates the need for conversion circuits and reduces power consumption compared to traditional electronic noses.
Article
Physics, Applied
Mohammad Javad Mirshojaeian Hosseini, Elisa Donati, Tomoyuki Yokota, Sunghoon Lee, Giacomo Indiveri, Takao Someya, Robert A. Nawrocki
Summary: Organic electronics have been used to implement an Integrate-and-Fire spiking neuron based on the Axon-Hillock CMOS circuit, demonstrating bio-compatibility and flexibility. This study showcases the operation characteristics and computing capabilities of the organic neuromorphic circuit, with low power dissipation.
JOURNAL OF PHYSICS D-APPLIED PHYSICS
(2021)
Article
Nanoscience & Nanotechnology
Joon-Kyu Han, Seong-Yun Yun, Ji-Man Yu, Seung-Bae Jeon, Yang-Kyu Choi
Summary: An artificial multisensory device for sensor computing is demonstrated using a single-transistor neuron (1T-neuron) for multimodal perception. The 1T-neuron simultaneously receives visual and thermal sensing signals and converts them into electrical signals in the form of spiking, which are then sent to a spiking neural network. This allows for realizing input neurons for multimodal sensing. By utilizing the optical and thermal behaviors of the 1T-neuron, visual and thermal sensing is achieved. A fingerprint recognition system is implemented to demonstrate the neuromorphic multimodal sensing system using the artificial multisensory 1T-neuron, which not only identifies genuine patterns but also detects forgeries.
ACS APPLIED MATERIALS & INTERFACES
(2023)
Article
Computer Science, Hardware & Architecture
Judicael Clair, Guy Eichler, Luca P. Carloni
Summary: This study presents the design of a neuromorphic hardware accelerator with a programmable interface and an optimizer for resource allocation. The experiments show that the optimized neuromorphic hardware can achieve higher speed and energy efficiency and can be used in synergy with other accelerators for various application purposes.
ACM TRANSACTIONS ON EMBEDDED COMPUTING SYSTEMS
(2023)
Article
Neurosciences
Alberto Patino-Saucedo, Horacio Rostro-Gonzalez, Teresa Serrano-Gotarredona, Bernabe Linares-Barranco
Summary: This work demonstrates that offline-trained Liquid State Machines (LSMs) implemented in the SpiNNaker neuromorphic processor can classify visual events, achieving state-of-the-art performance in the event-based N-MNIST dataset. The readout layer is trained using a variation of back-propagation-through-time (BPTT) for Spiking Neural Networks (SNNs), while the internal weights of the reservoir remain static. Results show that mapping the LSM from a Deep Learning framework to SpiNNaker does not affect the classification task performance. Additionally, weight quantization has a minimal impact on the performance of the LSM.
FRONTIERS IN NEUROSCIENCE
(2022)
Article
Computer Science, Artificial Intelligence
Luping Zhang, Fei Xu
Summary: The paper introduces the asynchronous spiking neural P system with rules on synapses (ASNPR system) and presents the ASNPRC system with coupled neurons. The computational power of the ASNPRC systems is investigated and it is proven that they are Turing universal function-computing devices. The results highlight the importance of coupled neurons in the computation power of ASNPR systems.
KNOWLEDGE-BASED SYSTEMS
(2022)
Article
Mathematics, Interdisciplinary Applications
Ciyan Zheng, Long Peng, Jason K. K. Eshraghian, Xiaoli Wang, Jian Cen, Herbert Ho-Ching Iu
Summary: This study presents a novel floating flux-controlled memcapacitor design that can be used for experimental verification of large-scale memcapacitor arrays. By dynamically modifying the membrane time constant, the memcapacitor brings about novel short-term memory dynamics.
INTERNATIONAL JOURNAL OF BIFURCATION AND CHAOS
(2022)
Article
Multidisciplinary Sciences
Rohit Abraham John, Nimesh Shah, Sujaya Kumar Vishwanath, Si En Ng, Benny Febriansyah, Metikoti Jagadeeswararao, Chip-Hong Chang, Arindam Basu, Nripan Mathews
Summary: The study explores the use of one-dimensional halide perovskite memristors to design security primitives for key generation and device authentication, offering a new solution to the challenge of efficient roots of trust for resource-constrained hardware.
NATURE COMMUNICATIONS
(2021)
Article
Engineering, Electrical & Electronic
Nimesh Shah, Durba Chatterjee, Brojogopal Sapui, Debdeep Mukhopadhyay, Arindam Basu
Summary: This paper introduces a Recurrence-based PUF circuit that utilizes feedback and XOR function to enhance ML-attack resistance while maintaining reliability, suitable for both analog and digital PUF cores.
IEEE JOURNAL ON EMERGING AND SELECTED TOPICS IN CIRCUITS AND SYSTEMS
(2021)
Article
Engineering, Electrical & Electronic
Sumon Kumar Bose, Deepak Singla, Arindam Basu
Summary: This article introduces an in-memory filtering technology that utilizes 6T-SRAM in-memory computing for image denoising, improving processing efficiency and energy savings. The new technology demonstrates excellent energy-saving performance while maintaining high algorithm accuracy and has promising application prospects.
IEEE JOURNAL OF SOLID-STATE CIRCUITS
(2022)
Article
Neurosciences
Jyotibdha Acharya, Arindam Basu, Robert Legenstein, Thomas Limbacher, Panayiota Poirazi, Xundong Wu
Summary: In this paper, the nonlinear computational power provided by dendrites in biological and artificial neurons is discussed. Biological evidence, plasticity rules, and their impact on biological learning assessed by computational models are briefly presented. The computational implications include improved expressivity, efficient resource utilization, utilization of internal learning signals, and enabling continual learning. Examples of using dendritic computations to solve real-world classification problems are discussed, categorized based on the methods of plasticity used. The convergence between concepts of deep learning and dendritic computations is highlighted, along with future research directions.
Article
Computer Science, Information Systems
Vivek Mohan, Deepak Singla, Tarun Pulluri, Andres Ussa, Pradeep Kumar Gopalakrishnan, Pao-Sheng Sun, Bharath Ramesh, Arindam Basu
Summary: This article presents a hybrid event-frame approach for low-power traffic monitoring using dynamic vision sensors (DVS). By optimizing memory and computational needs, a hardware-efficient processing pipeline is proposed. Experimental results show that the proposed method achieves similar accuracy to existing methods while significantly reducing computational requirements.
IEEE INTERNET OF THINGS JOURNAL
(2022)
Article
Engineering, Electrical & Electronic
Sumon Kumar Bose, Arindam Basu
Summary: This article proposes a region proposal network based on neuromorphic vision sensors for energy savings in Internet of Things traffic monitoring systems. The algorithm utilizes one-dimensional projection of images for edge detection, leading to high energy efficiency and throughput.
IEEE JOURNAL OF SOLID-STATE CIRCUITS
(2023)
Article
Engineering, Civil
Xinggan Peng, Rongzihan Song, Qi Cao, Yue Li, Dongshun Cui, Xiaofan Jia, Zhiping Lin, Guang-Bin Huang
Summary: This paper proposes a novel detection algorithm using in-vehicle cameras for illegal parking detection. A new dataset and a labeling method are also introduced. The experiments show that the proposed algorithm has strong illumination robustness in different operating environments.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2022)
Article
Engineering, Electrical & Electronic
Xueyong Zhang, Arindam Basu
Summary: Neuromorphic vision sensors (NVS) save energy and reduce data by asynchronously recording changes in temporal contrast. This article proposes a hybrid memory bitcell for event-based binary image (EBBI) frame from NVS, achieving better performance in image restoration and object region proposals.
IEEE JOURNAL OF SOLID-STATE CIRCUITS
(2023)
Article
Engineering, Biomedical
Xiaofan Jia, Sadeed Bin Sayed, Nahian Ibn Hasan, Luis J. Gomez, Guang-Bin Huang, Abdulkadir C. Yucel
Summary: This paper proposes a deep learning-based emulator called DeeptDCS for rapidly evaluating the current density induced by transcranial direct current stimulation (tDCS). The emulator utilizes Attention U-net model to generate the three-dimensional current density distribution across the entire head based on the volume conductor models of head tissues. By fine-tuning the model, the generalization ability of DeeptDCS to non-trained electrode configurations can be greatly enhanced. DeeptDCS provides satisfactorily accurate results and is significantly faster than a physics-based open-source simulator.
IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING
(2023)
Proceedings Paper
Computer Science, Artificial Intelligence
Vivek Mohan, Wee Peng Tay, Arindam Basu
Summary: This study explores a neural sensing architecture with neuromorphic compression and an address-event representation inspired readout protocol for next-gen, massively parallel wireless iBMI. The effects of neuromorphic compression on spike shape, spike detection accuracy, sensitivity, and false detection rate are assessed using quantitative metrics such as root-mean-square error and correlation coefficient between the original and recovered signal, to understand the impact of compression on downstream iBMI tasks. The results demonstrate that a data compression ratio of > 50 can be achieved by selectively transmitting event pulses generated in different modes, with a correlation coefficient of approximately 0.9 and a spike detection accuracy of over 90%.
2023 IEEE INTERNATIONAL SYMPOSIUM ON CIRCUITS AND SYSTEMS, ISCAS
(2023)
Proceedings Paper
Computer Science, Artificial Intelligence
Nimesh Shah, Arindam Basu
Summary: The reliability of hardware security devices in a System-On-Chip with IoT sensor nodes is crucial. A weak PUF fabricated in 65nm CMOS is designed for chip ID applications, utilizing OFF devices to achieve low instability and BER. The measurements show high reproducibility and throughput, making it a promising choice for integration with IoT devices.
2023 IEEE INTERNATIONAL SYMPOSIUM ON CIRCUITS AND SYSTEMS, ISCAS
(2023)
Article
Computer Science, Artificial Intelligence
Andres Ussa, Chockalingam Senthil Rajen, Tarun Pulluri, Deepak Singla, Jyotibdha Acharya, Gideon Fu Chuanrong, Arindam Basu, Bharath Ramesh
Summary: This article proposes a real-time, hybrid neuromorphic framework for object tracking and classification using event-based cameras. It addresses the challenge of deep learning inference on low-power, embedded platforms. A hardware-friendly object tracking scheme is implemented using a frame-based region proposal method and the frame-based object track input is converted back to spikes for classification. The proposed neuromorphic system is also compared to state-of-the-art methods and demonstrated in real-time and embedded applications.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Proceedings Paper
Engineering, Electrical & Electronic
Sumon Kumar Bose, Arindam Basu
IEEE ASIAN SOLID-STATE CIRCUITS CONFERENCE (A-SSCC 2021)
(2021)
Proceedings Paper
Computer Science, Hardware & Architecture
Yoo-Seung Won, Soham Chatterjee, Dirmanto Jap, Arindam Basu, Shivam Bhasin
Summary: This study demonstrates a cold boot attack method on NCS for recovering model architecture and some weights successfully, although there are errors in correcting the weights, they can be corrected using the knowledge distillation method.
2021 IEEE/ACM INTERNATIONAL CONFERENCE ON COMPUTER AIDED DESIGN (ICCAD)
(2021)
Proceedings Paper
Computer Science, Hardware & Architecture
Yoo-Seung Won, Soham Chatterjee, Dirmanto Jap, Shivam Bhasin, Arindam Basu
Summary: This paper demonstrates the vulnerability of deployed deep learning models to timing side-channel attacks, where adversaries can reconstruct the model by measuring the execution time of the inference. The attack is validated on Intel Compute Stick 2 and is highlighted for its high success rate in cross-device setting.
2021 INTERNATIONAL CONFERENCE ON ELECTRONICS, INFORMATION, AND COMMUNICATION (ICEIC)
(2021)
Article
Computer Science, Artificial Intelligence
Rui Lv, Dingheng Wang, Jiangbin Zheng, Zhao-Xu Yang
Summary: In this paper, the authors investigate tensor decomposition for neural network compression. They analyze the convergence and precision of tensor mapping theory, validate the rationality of tensor mapping and its superiority over traditional tensor approximation based on the Lottery Ticket Hypothesis. They propose an efficient method called 3D-KCPNet to compress 3D convolutional neural networks using the Kronecker canonical polyadic (KCP) tensor decomposition. Experimental results show that 3D-KCPNet achieves higher accuracy compared to the original baseline model and the corresponding tensor approximation model.
Article
Computer Science, Artificial Intelligence
Xiangkun He, Zhongxu Hu, Haohan Yang, Chen Lv
Summary: In this paper, a novel constrained multi-objective reinforcement learning algorithm is proposed for personalized end-to-end robotic control with continuous actions. The approach trains a single model using constraint design and a comprehensive index to achieve optimal policies based on user-specified preferences.
Article
Computer Science, Artificial Intelligence
Zhijian Zhuo, Bilian Chen, Shenbao Yu, Langcai Cao
Summary: In this paper, a novel method called Expansion with Contraction Method for Overlapping Community Detection (ECOCD) is proposed, which utilizes non-negative matrix factorization to obtain disjoint communities and applies expansion and contraction processes to adjust the degree of overlap. ECOCD is applicable to various networks with different properties and achieves high-quality overlapping community detection.
Article
Computer Science, Artificial Intelligence
Yizhe Zhu, Chunhui Zhang, Jialin Gao, Xin Sun, Zihan Rui, Xi Zhou
Summary: In this work, the authors propose a Contrastive Spatio-Temporal Distilling (CSTD) approach to improve the detection of high-compressed deepfake videos. The approach leverages spatial-frequency cues and temporal-contrastive alignment to fully exploit spatiotemporal inconsistency information.
Review
Computer Science, Artificial Intelligence
Laijin Meng, Xinghao Jiang, Tanfeng Sun
Summary: This paper provides a review of coverless steganographic algorithms, including the development process, known contributions, and general issues in image and video algorithms. It also discusses the security of coverless steganography from theoretical analysis to actual investigation for the first time.
Article
Computer Science, Artificial Intelligence
Yajie Bao, Tianwei Xing, Xun Chen
Summary: Visual question answering requires processing multi-modal information and effective reasoning. Neural-symbolic learning is a promising method, but current approaches lack uncertainty handling and can only provide a single answer. To address this, we propose a confidence based neural-symbolic approach that evaluates NN inferences and conducts reasoning based on confidence.
Article
Computer Science, Artificial Intelligence
Anh H. Vo, Bao T. Nguyen
Summary: Interior style classification is an interesting problem with potential applications in both commercial and academic domains. This project proposes a method named ISC-DeIT, which combines data-efficient image transformer architectures and knowledge distillation, to address the interior style classification problem. Experimental results demonstrate a significant improvement in predictive accuracy compared to other state-of-the-art methods.
Article
Computer Science, Artificial Intelligence
Shashank Kotyan, Danilo Vasconcellos Vargas
Summary: This article introduces a novel augmentation technique called Dynamic Scanning Augmentation to improve the accuracy and robustness of Vision Transformer (ViT). The technique leverages dynamic input sequences to adaptively focus on different patches, resulting in significant changes in ViT's attention mechanism. Experimental results demonstrate that Dynamic Scanning Augmentation outperforms ViT in terms of both robustness to adversarial attacks and accuracy against natural images.
Article
Computer Science, Artificial Intelligence
Hiba Alqasir, Damien Muselet, Christophe Ducottet
Summary: The article proposes a solution to improve the learning process of a classification network by providing shape priors, reducing the need for annotated data. The solution is tested on cross-domain digit classification tasks and a video surveillance application.
Article
Computer Science, Artificial Intelligence
Dexiu Ma, Mei Liu, Mingsheng Shang
Summary: This paper proposes a method using neural dynamics solvers to solve infinity-norm optimization problems. Two improved solvers are constructed and their effectiveness and superiority are demonstrated through theoretical analysis and simulation experiments.
Article
Computer Science, Artificial Intelligence
Francesco Gregoretti, Giovanni Pezzulo, Domenico Maisto
Summary: Active Inference is a computational framework that uses probabilistic inference and variational free energy minimization to describe perception, planning, and action. cpp-AIF is a header-only C++ library that provides a powerful tool for implementing Active Inference for Partially Observable Markov Decision Processes through multi-core computing. It is cross-platform and improves performance, memory management, and usability compared to existing software.
Article
Computer Science, Artificial Intelligence
Zelin Ying, Dawei Cheng, Cen Chen, Xiang Li, Peng Zhu, Yifeng Luo, Yuqi Liang
Summary: This paper proposes a novel stock market trends prediction framework called SMART, which includes a self-supervised stock technical data sequence embedding model S3E. By training with multiple self-supervised auxiliary tasks, the model encodes stock technical data sequences into embeddings and uses the learned sequence embeddings for predicting stock market trends. Extensive experiments on China A-Shares market and NASDAQ market prove the high effectiveness of our model in stock market trends prediction, and its effectiveness is further validated in real-world applications in a leading financial service provider in China.
Article
Computer Science, Artificial Intelligence
Hao Li, Hao Jiang, Dongsheng Ye, Qiang Wang, Liang Du, Yuanyuan Zeng, Liu Yuan, Yingxue Wang, C. Chen
Summary: DHGAT1, a dynamic hyperbolic graph attention network, utilizes hyperbolic metric properties to embed dynamic graphs. It employs a spatiotemporal self-attention mechanism and weighted node representations, resulting in excellent performance in link prediction tasks.
Article
Computer Science, Artificial Intelligence
Jiehui Huang, Zhenchao Tang, Xuedong He, Jun Zhou, Defeng Zhou, Calvin Yu-Chian Chen
Summary: This study proposes a progressive learning multi-scale feature blending model for image deraining tasks. The model utilizes detail dilation and texture extraction to improve the restoration of rainy images. Experimental results show that the model achieves near state-of-the-art performance in rain removal tasks and exhibits better rain removal realism.
Article
Computer Science, Artificial Intelligence
Lizhi Liu, Zilin Gao, Yinhe Wang, Yongfu Li
Summary: This paper proposes a novel discrete-time interconnected model for depicting complex dynamical networks. The model consists of nodes and edges subsystems, which consider the dynamic characteristic of both nodes and edges. By designing control strategies and coupling modes, the stabilization and synchronization of the network are achieved. Simulation results demonstrate the effectiveness of the proposed methods.