Article
Chemistry, Physical
Dawid Przyczyna, Krzysztof Mech, Ewelina Kowalewska, Mateusz Marzec, Tomasz Mazur, Piotr Zawal, Konrad Szacilowski
Summary: This paper reports on the successful electrodeposition of thin-film materials consisting of copper tungstate and copper molybdate, which exhibit notable memristive properties. The ability to switch between low and high resistive states and simulate bio-inspired effects on the material could offer energy and time savings for classical computations.
Article
Physics, Applied
K. Segall, C. Purmessur, A. D'Addario, D. Schult
Summary: The recent success of AI systems has led to an increase in computational resources which threatens the future development of AI systems. Unsupervised learning presents a possible solution, and a synaptic circuit made from superconducting electronics capable of STDP has been designed. The circuit demonstrates the hallmark behaviors of STDP through numerical simulation, and when combined with existing superconducting neuromorphic components, it could contribute to the creation of a fast, powerful, and energy-efficient Spiking Neural Network.
APPLIED PHYSICS LETTERS
(2023)
Article
Engineering, Electrical & Electronic
Dayanand Kumar, Aftab Saleem, Lai Boon Keong, Amit Singh, Yeong Her Wang, Tseung-Yuen Tseng
Summary: In this study, the synaptic features of a transparent bilayer memristor for neuromorphic computing applications were investigated. The device exhibited stable synaptic characteristics, including potentiation and depression, as well as highly linear synaptic features. The bilayer transparent synapse also showed good retention property, multi-level cell characteristics, and high potential for future neuromorphic computing systems.
IEEE ELECTRON DEVICE LETTERS
(2022)
Article
Engineering, Multidisciplinary
Ahmet Yasin Baran, Nimet Korkmaz, Ismail Ozturk, Recai Kilic
Summary: This study investigates the correlation between the Spike-Time-Dependent-Plasticity (STDP) learning rule and the memristor-based synapse structure. By coupling two HR neurons with a memductance structure, the STDP learning rule is validated as an alternative viewpoint in neuromorphic studies. The study confirms the feasibility of using memristor devices as alternative synapse definitions through numerical simulation comparisons.
ENGINEERING SCIENCE AND TECHNOLOGY-AN INTERNATIONAL JOURNAL-JESTECH
(2022)
Article
Physics, Applied
Brandon Sueoka, Feng Zhao
Summary: In this study, the potential of a honey-based organic memristor for SNNs was demonstrated. The device exhibited forming-free bipolar resistive switching, high-speed switching characteristics, and the ability to dissolve in water. Intuitive conduction models for STDP and SRDP were proposed. These results highlight the promise of honey-based memristive synaptic devices for SNN implementation in green electronics and biodegradable neuromorphic systems.
JOURNAL OF PHYSICS D-APPLIED PHYSICS
(2022)
Article
Chemistry, Multidisciplinary
Minkang Kim, Dongyeol Ju, Myounggon Kang, Sungjun Kim
Summary: In this study, the electrical properties of ITO/ZrOx/TaN RRAM devices for neuromorphic computing applications were investigated. The thickness and material composition of the device were analyzed using transmission electron microscopy. The forming process of the ZrOx-based device was divided into single- and double-forming methods, and their resistive switching behaviors were compared, along with synaptic simulations and pattern recognition system applications.
Review
Computer Science, Information Systems
Bonan Yan, Yuchao Yang, Ru Huang
Summary: This paper reviews the latest advances in novel types of memristors and their applications in bio-inspired computing systems and sensory systems. The paper also discusses device-circuit co-optimization methods and offers insights into the research trends of memristive materials and devices.
SCIENCE CHINA-INFORMATION SCIENCES
(2023)
Article
Engineering, Electrical & Electronic
Mahmudul Alam Shakib, Zhaolin Gao, Caterina Lamuta
Summary: This study investigates different types of synaptic plasticity properties of geopolymer memristors, demonstrating short-term and long-term memory, Hebbian learning inspired spike-timing-dependent plasticity, spike-rate-dependent plasticity, history-dependent plasticity, paired-pulse facilitation, paired-pulse depression, and post-tetanic potentiation. These properties are attributed to the movement of ions induced by electro-osmosis in the capillaries and pores of the geopolymer memristors. They show great potential for the use of geopolymers in neuromorphic computing applications.
ACS APPLIED ELECTRONIC MATERIALS
(2023)
Article
Engineering, Electrical & Electronic
Yuki Shibayama, Yuki Ohnishi, Tetsuya Katagiri, Yuhei Yamamoto, Yasuhiko Nakashima, Mutsumi Kimura
Summary: An amorphous-metal-oxide-semiconductor (AOS) thin-film planar-type spike-timing-dependent-plasticity (STDP) synapse device has been developed, showing promising characteristics for learning in neuromorphic systems. The STDP device is cost-effective and demonstrates long-term potentiation (LTP) and long-term depression (LTD) due to charge injection into the underlayer insulator film.
IEEE ELECTRON DEVICE LETTERS
(2021)
Article
Neurosciences
Nan Du, Xianyue Zhao, Ziang Chen, Bhaskar Choubey, Massimiliano Di Ventra, Ilona Skorupa, Danilo Buerger, Heidemarie Schmidt
Summary: BiFeO3(BFO) artificial synapses exhibit various long-term plasticity functions depending on time, cycles, and frequency, with their learning windows capable of wide time scale configurability based on applied waveforms. In addition, a study on generalized frequency-dependent plasticity reveals that modulation of pulse width and pulse interval time within one spike cycle can lead to both synaptic potentiation and depression effects.
FRONTIERS IN NEUROSCIENCE
(2021)
Article
Engineering, Electrical & Electronic
Doohyeok Lim
Summary: In this paper, a single silicon synaptic device with stochastic binary spike-timing-dependent plasticity is presented. Implementing the device using standard complementary metal-oxide-semiconductor technology, it resembles a conventional metal-oxide-semiconductor field-effect transistor structure. Experimental results demonstrate the stochastic nature of the feedback mechanism induced by weak impact ionization.
SEMICONDUCTOR SCIENCE AND TECHNOLOGY
(2023)
Article
Computer Science, Artificial Intelligence
Zhiri Tang, Yanhua Chen, Zhihua Wang, Ruihan Hu, Edmond Q. Wu
Summary: The proposed non-STDP learning mechanism shows good hardware performance in both feedforward neural network and crossbar frameworks, saving hardware resources and improving processing speed compared to STDP-based methods. Further exploration of complex memristor models with non-STDP learning mechanisms is recommended for practical applications of memristive neural networks.
APPLIED INTELLIGENCE
(2021)
Article
Computer Science, Artificial Intelligence
Marcin Bialas, Jacek Mandziuk
Summary: This article proposes an effective variant of STDP extended by an activation-dependent scale factor, serving as an efficient mechanism for the unsupervised development of RFs. The importance of synaptic scaling and lateral inhibition in the successful development of RFs is demonstrated, with the significance of maintaining high levels of synaptic scaling highlighted. Experimental results show that the proposed solution performs well in classification tasks on the MNIST dataset.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2022)
Article
Materials Science, Multidisciplinary
Jing Zhang, Tao Yang, Jingjuan Wang, Jianhui Zhao, Xiaobing Yan
Summary: In this study, a novel memristor TTHZOP was designed based on the memristive properties of tantalum dioxide. The device conductance can be continuously tuned by adjusting voltage pulse parameters, and shows a gradual distribution adjustment in successive cycles.
SCIENCE CHINA-MATERIALS
(2021)
Article
Computer Science, Information Systems
Guilei Ma, Menghua Man, Yongqiang Zhang, Shanghe Liu
Summary: This paper presents a circuit design with a fast homeostatic inhibitory plasticity rule by imitating the mechanism of the biological nervous system. The circuit is validated using a memristive synapse, and the simulation results show that it can achieve similar weight update curves as the biological mechanism but with a significant improvement in time scale. Additionally, the circuit has wide applicability due to its adjustable homeostatic learning window, scaling factor, and homeostatic factor. This study offers new opportunities for building fast and reliable neuromorphic hardware.
Article
Computer Science, Theory & Methods
Iman Esmaili Paeen Afrakoti, Saeed Bagheri Shouraki, Farnood Merrikh Bayat, Mohammad Gholami
FUZZY SETS AND SYSTEMS
(2017)
Article
Biology
Seyed Abolfazl Hosseini, Iman Esmaili Paeen Afrakoti
JOURNAL OF RADIATION RESEARCH
(2018)
Article
Nuclear Science & Technology
Seyed Abolfazl Hosseini, Iman Esmaili Paeen Afrakoti
NUCLEAR ENGINEERING AND TECHNOLOGY
(2017)
Article
Instruments & Instrumentation
Seyed Abolfazl Hosseini, Iman Esmaili Paeen Afrakoti
NUCLEAR INSTRUMENTS & METHODS IN PHYSICS RESEARCH SECTION A-ACCELERATORS SPECTROMETERS DETECTORS AND ASSOCIATED EQUIPMENT
(2017)
Article
Nuclear Science & Technology
Seyed Abolfazi Hosseini, Iman Esmaili Paeen Afrakoti
ANNALS OF NUCLEAR ENERGY
(2018)
Article
Computer Science, Artificial Intelligence
Sajad Haghzad Klidbary, Saeed Bagheri Shouraki, Iman Esmaili Paeen Afrakoti
NEURAL COMPUTING & APPLICATIONS
(2019)
Article
Computer Science, Information Systems
Iman Esmaili Paeen Afrakoti, Saeed Bagheri Shouraki, Bahar Haghighat
IEEE SYSTEMS JOURNAL
(2014)
Article
Computer Science, Artificial Intelligence
Hesam Sagha, Iman Esmaili Paeen Afrakoti, Saeed Bagherishouraki
TURKISH JOURNAL OF ELECTRICAL ENGINEERING AND COMPUTER SCIENCES
(2013)
Article
Instruments & Instrumentation
S. A. Hosseini, I. E. P. Afrakoti, M. Mehrabi, M. Zangian
JOURNAL OF INSTRUMENTATION
(2019)
Article
Engineering, Electrical & Electronic
Iman E. P. Afrakoti, Vahdat Nazerian
RECENT ADVANCES IN ELECTRICAL & ELECTRONIC ENGINEERING
(2020)
Article
Engineering, Multidisciplinary
M. Shavandi, I. E. P. Afrakoti
INTERNATIONAL JOURNAL OF ENGINEERING
(2019)
Article
Nuclear Science & Technology
Seyed Abolfazl Hosseini, Iman Esmaili Paeen Afrakoti
ANNALS OF NUCLEAR ENERGY
(2017)
Proceedings Paper
Computer Science, Artificial Intelligence
Iman Esmaili Paeen Afrakoti, Aboozar Ghaffari, Saeed Bagheri Shouraki
2013 FIRST IRANIAN CONFERENCE ON PATTERN RECOGNITION AND IMAGE ANALYSIS (PRIA)
(2013)
Proceedings Paper
Computer Science, Artificial Intelligence
Iman Esmaili Paeen Afrakoti, Saeed Bagheri Shouraki, Aboozar Ghaffari
2013 FIRST IRANIAN CONFERENCE ON PATTERN RECOGNITION AND IMAGE ANALYSIS (PRIA)
(2013)
Article
Computer Science, Artificial Intelligence
Mohsen Firouzi, Saeed Bagheri Shouraki, Iman Esmaili Paeen Afrakoti
JOURNAL OF INTELLIGENT & FUZZY SYSTEMS
(2014)
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.