Pub Date : 2024-05-10DOI: 10.1088/2634-4386/ad49ce
Muhammad Sabbir Alam, Walid Al Misba, J. Atulasimha
Anomaly detection in real-time using autoencoders implemented on edge devices is exceedingly challenging due to limited hardware, energy, and computational resources. We show that these limitations can be addressed by designing an autoencoder with low-resolution non-volatile memory-based synapses and employing an effective quantized neural network learning algorithm. We further propose nanoscale ferromagnetic racetracks with engineered notches hosting magnetic domain walls (DW) as exemplary non-volatile memory based autoencoder synapses, where limited state (5-state) synaptic weights are manipulated by spin orbit torque (SOT) current pulses to write different magnetoresistance states. The performance of anomaly detection of the proposed autoencoder model is evaluated on the NSL-KDD dataset. Limited resolution and DW device stochasticity aware training of the autoencoder is performed, which yields comparable anomaly detection performance to the autoencoder having floating-point precision weights. While the limited number of quantized states and the inherent stochastic nature of DW synaptic weights in nanoscale devices are typically known to negatively impact the performance, our hardware-aware training algorithm is shown to leverage these imperfect device characteristics to generate an improvement in anomaly detection accuracy (90.98%) compared to accuracy obtained with floating-point synaptic weights that are extremely memory intensive. Furthermore, our DW-based approach demonstrates a remarkable reduction of at least three orders of magnitude in weight updates during training compared to the floating-point approach, implying significant reduction in operation energy for our method. This work could stimulate the development of extremely energy efficient non-volatile multi-state synapse-based processors that can perform real-time training and inference on the edge with unsupervised data.
{"title":"Quantized non-volatile nanomagnetic domain wall synapse based autoencoder for efficient unsupervised network anomaly detection","authors":"Muhammad Sabbir Alam, Walid Al Misba, J. Atulasimha","doi":"10.1088/2634-4386/ad49ce","DOIUrl":"https://doi.org/10.1088/2634-4386/ad49ce","url":null,"abstract":"\u0000 Anomaly detection in real-time using autoencoders implemented on edge devices is exceedingly challenging due to limited hardware, energy, and computational resources. We show that these limitations can be addressed by designing an autoencoder with low-resolution non-volatile memory-based synapses and employing an effective quantized neural network learning algorithm. We further propose nanoscale ferromagnetic racetracks with engineered notches hosting magnetic domain walls (DW) as exemplary non-volatile memory based autoencoder synapses, where limited state (5-state) synaptic weights are manipulated by spin orbit torque (SOT) current pulses to write different magnetoresistance states. The performance of anomaly detection of the proposed autoencoder model is evaluated on the NSL-KDD dataset. Limited resolution and DW device stochasticity aware training of the autoencoder is performed, which yields comparable anomaly detection performance to the autoencoder having floating-point precision weights. While the limited number of quantized states and the inherent stochastic nature of DW synaptic weights in nanoscale devices are typically known to negatively impact the performance, our hardware-aware training algorithm is shown to leverage these imperfect device characteristics to generate an improvement in anomaly detection accuracy (90.98%) compared to accuracy obtained with floating-point synaptic weights that are extremely memory intensive. Furthermore, our DW-based approach demonstrates a remarkable reduction of at least three orders of magnitude in weight updates during training compared to the floating-point approach, implying significant reduction in operation energy for our method. This work could stimulate the development of extremely energy efficient non-volatile multi-state synapse-based processors that can perform real-time training and inference on the edge with unsupervised data.","PeriodicalId":198030,"journal":{"name":"Neuromorphic Computing and Engineering","volume":" 22","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-05-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140991497","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-05-01DOI: 10.1088/2634-4386/ad462b
N. N. Chakraborty, Shelah Ameli, Hritom Das, C. Schuman, Garrett S. Rose
In neuromorphic computing, different learning mechanisms are being widely adopted to improve the performance of a specific application. Among these techniques, Spike-Timing-Dependent Plasticity (STDP) stands out as one of the most favored. STDP is simply managed by the temporal information of an event, which is biologically inspired. However, most of the prior works on STDP are focused on circuit implementation or software simulation for performance evaluation. Previous works also lack a comparative analysis of the performances of different STDP implementations. This study aims to provide a comprehensive assessment of STDP, centering on the performance across various applications such as classification (static and temporal datasets), control, and reservoir computing. Different applications necessitate distinct STDP configurations to achieve optimal performance with the neuroprocessor. Additionally, this work introduces an Application-Specific Integrated Circuit (ASIC) design of STDP circuitry. The design is based on current-controlled memristive synapse principles and utilizes 65nm CMOS technology from IBM. The detailed presentation includes circuitry specifics, layout, and performance parameters such as energy consumption and design area.
{"title":"Hardware software co-design for leveraging STDP in a memristive neuroprocessor","authors":"N. N. Chakraborty, Shelah Ameli, Hritom Das, C. Schuman, Garrett S. Rose","doi":"10.1088/2634-4386/ad462b","DOIUrl":"https://doi.org/10.1088/2634-4386/ad462b","url":null,"abstract":"\u0000 In neuromorphic computing, different learning mechanisms are being widely adopted to improve the performance of a specific application. Among these techniques, Spike-Timing-Dependent Plasticity (STDP) stands out as one of the most favored. STDP is simply managed by the temporal information of an event, which is biologically inspired. However, most of the prior works on STDP are focused on circuit implementation or software simulation for performance evaluation. Previous works also lack a comparative analysis of the performances of different STDP implementations. This study aims to provide a comprehensive assessment of STDP, centering on the performance across various applications such as classification (static and temporal datasets), control, and reservoir computing. Different applications necessitate distinct STDP configurations to achieve optimal performance with the neuroprocessor. Additionally, this work introduces an Application-Specific Integrated Circuit (ASIC) design of STDP circuitry. The design is based on current-controlled memristive synapse principles and utilizes 65nm CMOS technology from IBM. The detailed presentation includes circuitry specifics, layout, and performance parameters such as energy consumption and design area.","PeriodicalId":198030,"journal":{"name":"Neuromorphic Computing and Engineering","volume":"6 4","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141038758","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-04-23DOI: 10.1088/2634-4386/ad4209
Raz Halaly, Elishai Ezra Tsur
Model Predictive Control (MPC) is a prominent control paradigm providing accurate state prediction and subsequent control actions for intricate dynamical systems with applications ranging from autonomous driving to star tracking. However, there is an apparent discrepancy between the model’s mathematical description and its behavior in real-world conditions, affecting its performance in real-time. In this work, we propose a novel neuromorphic spiking neural network for continuous adaptive non-linear MPC. By using real-time learning, our design significantly reduces dynamic error and augments model accuracy, while simultaneously addressing unforeseen situations. We evaluated our framework using real-world scenarios in autonomous driving, implemented in a physics-driven simulation. We tested our design with various vehicles (from a Tesla Model 3 to an Ambulance) experiencing malfunctioning and swift steering scenarios. We demonstrate significant improvements in dynamic error rate compared with traditional MPC implementation with up to 89.87% median prediction error reduction with 5 spiking neurons and up to 96.95% with 5000 neurons. Our results may pave the way for novel applications in real-time control and stimulate further studies in the adaptive control realm with spiking neural networks.
{"title":"Continuous adaptive nonlinear model predictive control using spiking neural networks and real-time learning","authors":"Raz Halaly, Elishai Ezra Tsur","doi":"10.1088/2634-4386/ad4209","DOIUrl":"https://doi.org/10.1088/2634-4386/ad4209","url":null,"abstract":"\u0000 Model Predictive Control (MPC) is a prominent control paradigm providing accurate state prediction and subsequent control actions for intricate dynamical systems with applications ranging from autonomous driving to star tracking. However, there is an apparent discrepancy between the model’s mathematical description and its behavior in real-world conditions, affecting its performance in real-time. In this work, we propose a novel neuromorphic spiking neural network for continuous adaptive non-linear MPC. By using real-time learning, our design significantly reduces dynamic error and augments model accuracy, while simultaneously addressing unforeseen situations. We evaluated our framework using real-world scenarios in autonomous driving, implemented in a physics-driven simulation. We tested our design with various vehicles (from a Tesla Model 3 to an Ambulance) experiencing malfunctioning and swift steering scenarios. We demonstrate significant improvements in dynamic error rate compared with traditional MPC implementation with up to 89.87% median prediction error reduction with 5 spiking neurons and up to 96.95% with 5000 neurons. Our results may pave the way for novel applications in real-time control and stimulate further studies in the adaptive control realm with spiking neural networks.","PeriodicalId":198030,"journal":{"name":"Neuromorphic Computing and Engineering","volume":"126 2","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140668936","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-04-19DOI: 10.1088/2634-4386/ad409a
Chang-Jae Beak, Jihwan Lee, Junseok Kim, Jiwoo Park, Sin-Hyung Lee
A filamentary-based organic memristor is a promising synaptic component for the development of neuromorphic systems for wearable electronics. In the organic memristors, metallic conductive filaments (CF) are formed via electrochemical metallization under electric stimuli, and it results in the resistive switching characteristics. To realize the bio-inspired computing systems utilizing the organic memristors, it is essential to effectively engineer the CF growth for emulating the complete synaptic functions in the device. Here, the fundamental principles underlying the operation of organic memristors and parameters related to CF growth are discussed. Additionally, recent studies that focused on controlling CF growth to replicate synaptic functions, including reproducible resistive switching, continuous conductance levels, and synaptic plasticity, are reviewed. Finally, upcoming research directions in the field of organic memristors for wearable smart computing systems are suggested.
{"title":"Filamentary-based organic memristors for wearable neuromorphic computing systems","authors":"Chang-Jae Beak, Jihwan Lee, Junseok Kim, Jiwoo Park, Sin-Hyung Lee","doi":"10.1088/2634-4386/ad409a","DOIUrl":"https://doi.org/10.1088/2634-4386/ad409a","url":null,"abstract":"\u0000 A filamentary-based organic memristor is a promising synaptic component for the development of neuromorphic systems for wearable electronics. In the organic memristors, metallic conductive filaments (CF) are formed via electrochemical metallization under electric stimuli, and it results in the resistive switching characteristics. To realize the bio-inspired computing systems utilizing the organic memristors, it is essential to effectively engineer the CF growth for emulating the complete synaptic functions in the device. Here, the fundamental principles underlying the operation of organic memristors and parameters related to CF growth are discussed. Additionally, recent studies that focused on controlling CF growth to replicate synaptic functions, including reproducible resistive switching, continuous conductance levels, and synaptic plasticity, are reviewed. Finally, upcoming research directions in the field of organic memristors for wearable smart computing systems are suggested.","PeriodicalId":198030,"journal":{"name":"Neuromorphic Computing and Engineering","volume":" 689","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140681992","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-04-08DOI: 10.1088/2634-4386/ad3be7
Felix Wang, Shruti Kulkarni, Bradley H. Theilman, Fredrick Rothganger, C. Schuman, Seung-Hwan Lim, J. Aimone
As modern neuroscience tools acquire more details about the brain, the need to move towards biological-scale neural simulations continues to grow. However, effective simulations at scale remain a challenge. Beyond just the tooling required to enable parallel execution, there is also the unique structure of the synaptic interconnectivity, which is globally sparse but has relatively high connection density and non-local interactions per neuron. There are also various practicalities to consider in high performance computing applications, such as the need for serializing neural networks to support potentially long-running simulations that require checkpoint-restart. Although acceleration on neuromorphic hardware is also a possibility, development in this space can be difficult as hardware support tends to vary between platforms and software support for larger scale models also tends to be limited. In this paper, we focus our attention on STACS (Simulation Tool for Asynchronous Cortical Streams), a spiking neural network simulator that leverages the Charm++ parallel programming framework, with the goal of supporting biological-scale simulations as well as interoperability between platforms. Central to these goals is the implementation of scalable data structures suitable for efficiently distributing a network across parallel partitions. Here, we discuss a straightforward extension of a parallel data format with a history of use in graph partitioners, which also serves as a portable intermediate representation for different neuromorphic backends. We perform scaling studies on the Summit supercomputer, examining the capabilities of STACS in terms of network build and storage, partitioning, and execution. We highlight how a suitably partitioned, spatially dependent synaptic structure introduces a communication workload well-suited to the multicast communication supported by Charm++. We evaluate the strong and weak scaling behavior for networks on the order of millions of neurons and billions of synapses, and show that STACS achieves competitive levels of parallel efficiency.
{"title":"Scaling neural simulations in STACS","authors":"Felix Wang, Shruti Kulkarni, Bradley H. Theilman, Fredrick Rothganger, C. Schuman, Seung-Hwan Lim, J. Aimone","doi":"10.1088/2634-4386/ad3be7","DOIUrl":"https://doi.org/10.1088/2634-4386/ad3be7","url":null,"abstract":"\u0000 As modern neuroscience tools acquire more details about the brain, the need to move towards biological-scale neural simulations continues to grow. However, effective simulations at scale remain a challenge. Beyond just the tooling required to enable parallel execution, there is also the unique structure of the synaptic interconnectivity, which is globally sparse but has relatively high connection density and non-local interactions per neuron. There are also various practicalities to consider in high performance computing applications, such as the need for serializing neural networks to support potentially long-running simulations that require checkpoint-restart. Although acceleration on neuromorphic hardware is also a possibility, development in this space can be difficult as hardware support tends to vary between platforms and software support for larger scale models also tends to be limited. In this paper, we focus our attention on STACS (Simulation Tool for Asynchronous Cortical Streams), a spiking neural network simulator that leverages the Charm++ parallel programming framework, with the goal of supporting biological-scale simulations as well as interoperability between platforms. Central to these goals is the implementation of scalable data structures suitable for efficiently distributing a network across parallel partitions. Here, we discuss a straightforward extension of a parallel data format with a history of use in graph partitioners, which also serves as a portable intermediate representation for different neuromorphic backends. We perform scaling studies on the Summit supercomputer, examining the capabilities of STACS in terms of network build and storage, partitioning, and execution. We highlight how a suitably partitioned, spatially dependent synaptic structure introduces a communication workload well-suited to the multicast communication supported by Charm++. We evaluate the strong and weak scaling behavior for networks on the order of millions of neurons and billions of synapses, and show that STACS achieves competitive levels of parallel efficiency.","PeriodicalId":198030,"journal":{"name":"Neuromorphic Computing and Engineering","volume":"45 5","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140729570","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-04-04DOI: 10.1088/2634-4386/ad3a96
Michele Di Lauro, Federico Rondelli, Anna De Salvo, Alessandro Corsini, Matteo Genitoni, Pierpaolo Greco, Mauro Murgia, L. Fadiga, Fabio Biscarini
A novel organic neuromorphic device performing pattern classification is presented and demonstrated. It features an artificial soma capable of dendritic integration from three pre-synaptic neurons. The time response of the interface between electrolytic solutions and organic mixed ionic-electronic conductors is proposed as the sole computational feature for pattern recognition, and it is easily tuned in the organic dendritic integrator by simply controlling electrolyte ionic strength. The classifier is benchmarked in speech-recognition experiments, with a sample of fourteen words, encoded either from audio tracks or from kinematic data, showing excellent discrimination performances in a planar, miniaturizable, fully passive device, designed to be promptly integrated in more complex architectures where on-board pattern classification is required.
{"title":"An organic artificial soma for spatio-temporal pattern recognition via dendritic integration","authors":"Michele Di Lauro, Federico Rondelli, Anna De Salvo, Alessandro Corsini, Matteo Genitoni, Pierpaolo Greco, Mauro Murgia, L. Fadiga, Fabio Biscarini","doi":"10.1088/2634-4386/ad3a96","DOIUrl":"https://doi.org/10.1088/2634-4386/ad3a96","url":null,"abstract":"\u0000 A novel organic neuromorphic device performing pattern classification is presented and demonstrated. It features an artificial soma capable of dendritic integration from three pre-synaptic neurons. The time response of the interface between electrolytic solutions and organic mixed ionic-electronic conductors is proposed as the sole computational feature for pattern recognition, and it is easily tuned in the organic dendritic integrator by simply controlling electrolyte ionic strength. The classifier is benchmarked in speech-recognition experiments, with a sample of fourteen words, encoded either from audio tracks or from kinematic data, showing excellent discrimination performances in a planar, miniaturizable, fully passive device, designed to be promptly integrated in more complex architectures where on-board pattern classification is required.","PeriodicalId":198030,"journal":{"name":"Neuromorphic Computing and Engineering","volume":"8 13","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140745875","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-02-02DOI: 10.1088/2634-4386/ad207c
Dennis Meier, Jorge Íñiguez-González, D. Rodrigues, Karin Everschor-Sitte
{"title":"Editorial: Focus issue on topological solitons for neuromorphic systems","authors":"Dennis Meier, Jorge Íñiguez-González, D. Rodrigues, Karin Everschor-Sitte","doi":"10.1088/2634-4386/ad207c","DOIUrl":"https://doi.org/10.1088/2634-4386/ad207c","url":null,"abstract":"","PeriodicalId":198030,"journal":{"name":"Neuromorphic Computing and Engineering","volume":"6 3","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139871200","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-02-02DOI: 10.1088/2634-4386/ad207c
Dennis Meier, Jorge Íñiguez-González, D. Rodrigues, Karin Everschor-Sitte
{"title":"Editorial: Focus issue on topological solitons for neuromorphic systems","authors":"Dennis Meier, Jorge Íñiguez-González, D. Rodrigues, Karin Everschor-Sitte","doi":"10.1088/2634-4386/ad207c","DOIUrl":"https://doi.org/10.1088/2634-4386/ad207c","url":null,"abstract":"","PeriodicalId":198030,"journal":{"name":"Neuromorphic Computing and Engineering","volume":"4 4","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139811178","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-11-27DOI: 10.1088/2634-4386/ad0fec
Pathik Sahoo, Pushpendra Singh, Komal Saxena, Subrata Ghosh, Ravindra P. Singh, R. Benosman, Jonathan P. Hill, Tomonobu Nakayama, A. Bandyopadhyay
To build energy minimized superstructures, self-assembling molecules explore astronomical options, colliding ∼109 molecules s−1. Thus far, no computer has used it fully to optimize choices and execute advanced computational theories only by synthesizing supramolecules. To realize it, first, we remotely re-wrote the problem in a language that supramolecular synthesis comprehends. Then, all-chemical neural network synthesizes one helical nanowire for one periodic event. These nanowires self-assemble into gel fibers mapping intricate relations between periodic events in any-data-type, the output is read instantly from optical hologram. Problem-wise, self-assembling layers or neural network depth is optimized to chemically simulate theories discovering invariants for learning. Subsequently, synthesis alone solves classification, feature learning problems instantly with single shot training. Reusable gel begins general-purpose computing that would chemically invent suitable models for problem-specific unsupervised learning. Irrespective of complexity, keeping fixed computing time and power, gel promises a toxic-hardware-free world. One sentence summary: fractally coupled deep learning networks revisits Rosenblatt’s 1950s theorem on deep learning network.
{"title":"A general-purpose organic gel computer that learns by itself","authors":"Pathik Sahoo, Pushpendra Singh, Komal Saxena, Subrata Ghosh, Ravindra P. Singh, R. Benosman, Jonathan P. Hill, Tomonobu Nakayama, A. Bandyopadhyay","doi":"10.1088/2634-4386/ad0fec","DOIUrl":"https://doi.org/10.1088/2634-4386/ad0fec","url":null,"abstract":"To build energy minimized superstructures, self-assembling molecules explore astronomical options, colliding ∼109 molecules s−1. Thus far, no computer has used it fully to optimize choices and execute advanced computational theories only by synthesizing supramolecules. To realize it, first, we remotely re-wrote the problem in a language that supramolecular synthesis comprehends. Then, all-chemical neural network synthesizes one helical nanowire for one periodic event. These nanowires self-assemble into gel fibers mapping intricate relations between periodic events in any-data-type, the output is read instantly from optical hologram. Problem-wise, self-assembling layers or neural network depth is optimized to chemically simulate theories discovering invariants for learning. Subsequently, synthesis alone solves classification, feature learning problems instantly with single shot training. Reusable gel begins general-purpose computing that would chemically invent suitable models for problem-specific unsupervised learning. Irrespective of complexity, keeping fixed computing time and power, gel promises a toxic-hardware-free world. One sentence summary: fractally coupled deep learning networks revisits Rosenblatt’s 1950s theorem on deep learning network.","PeriodicalId":198030,"journal":{"name":"Neuromorphic Computing and Engineering","volume":"48 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-11-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139233853","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-11-07DOI: 10.1088/2634-4386/ad06ca
Y. van de Burgt, Francesca Santoro, Benjamin Tee, Fabien Alibart
Artificial intelligence (AI) and deep learning rely on artificial neural networks that are typically executed on conventional von Neumann architecture-based computers, mostly operating in a sequential manner. In contrast
{"title":"Editorial: Focus on organic materials, bio-interfacing and processing in neuromorphic computing and artificial sensory applications","authors":"Y. van de Burgt, Francesca Santoro, Benjamin Tee, Fabien Alibart","doi":"10.1088/2634-4386/ad06ca","DOIUrl":"https://doi.org/10.1088/2634-4386/ad06ca","url":null,"abstract":"Artificial intelligence (AI) and deep learning rely on artificial neural networks that are typically executed on conventional von Neumann architecture-based computers, mostly operating in a sequential manner. In contrast","PeriodicalId":198030,"journal":{"name":"Neuromorphic Computing and Engineering","volume":"6 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139286452","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：