Microrobots with simultaneously improved degradability and mechanical strength are highly demanded in performing in vivo delivery tasks in clinical applications. The properties of degradability and mechanical strength are contradictory for many materials used to make microrobots. This article proposes a new design that can result in 3D cell culture microrobots with improved degradability and mechanical strength from the following perspectives. First, the mechanical strength of a microrobot is improved using triangle patterns to replace hexagon pattern in the microrobot structure, which can provide more supporting grids to obtain increased mechanical strength. Second, the relationship between structural design and material composition in relation to the mechanical strength of microrobot is investigated. The study reveals that triangle‐patterned microrobots have increased mechanical strength compared with hexagon‐patterned microrobots, thereby allowing high composition of degradable material that leads to the fast degradation of the microrobot. It is also shown that the triangle‐patterned microrobots can maintain the same structural integrity and cell capacity as hexagon‐patterned microrobots. Finally, the demonstration shows that the triangle‐patterned microrobot can be precisely navigated in microfluidic channels. This article successfully demonstrates that the degradability and mechanical strength can be improved simultaneously through the microrobot structural design.
{"title":"Development of a Cell‐Loading Microrobot with Simultaneously Improved Degradability and Mechanical Strength for Performing In Vivo Delivery Tasks","authors":"Tanyong Wei, Junyang Li, Liushuai Zheng, Cheng Wang, Feng Li, Hua Tian, Dong Sun","doi":"10.1002/aisy.202100052","DOIUrl":"https://doi.org/10.1002/aisy.202100052","url":null,"abstract":"Microrobots with simultaneously improved degradability and mechanical strength are highly demanded in performing in vivo delivery tasks in clinical applications. The properties of degradability and mechanical strength are contradictory for many materials used to make microrobots. This article proposes a new design that can result in 3D cell culture microrobots with improved degradability and mechanical strength from the following perspectives. First, the mechanical strength of a microrobot is improved using triangle patterns to replace hexagon pattern in the microrobot structure, which can provide more supporting grids to obtain increased mechanical strength. Second, the relationship between structural design and material composition in relation to the mechanical strength of microrobot is investigated. The study reveals that triangle‐patterned microrobots have increased mechanical strength compared with hexagon‐patterned microrobots, thereby allowing high composition of degradable material that leads to the fast degradation of the microrobot. It is also shown that the triangle‐patterned microrobots can maintain the same structural integrity and cell capacity as hexagon‐patterned microrobots. Finally, the demonstration shows that the triangle‐patterned microrobot can be precisely navigated in microfluidic channels. This article successfully demonstrates that the degradability and mechanical strength can be improved simultaneously through the microrobot structural design.","PeriodicalId":7187,"journal":{"name":"Advanced Intelligent Systems","volume":"1 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88223192","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}
Hyungyo Kim, Joon Hwang, D. Kwon, Jangsaeng Kim, Min-Kyu Park, Ji-Young Im, Byung-Gook Park, Jong-Ho Lee
On‐chip training of neural networks (NNs) is regarded as a promising training method for neuromorphic systems with analog synaptic devices. Herein, a novel on‐chip training method called direct gradient calculation (DGC) is proposed to substitute conventional backpropagation (BP). In this method, the gradients of a cost function with respect to the weights are calculated directly by sequentially applying a small temporal change to each weight and then measuring the change in cost value. DGC achieves a similar accuracy to that of BP while performing a handwritten digit classification task, validating its training feasibility. In particular, DGC can be applied to analog hardware‐based convolutional NNs (CNNs), which is considered to be a challenging task, enabling appropriate on‐chip training. A hybrid method is also proposed that efficiently combines DGC and BP for training CNNs, and the method achieves a similar accuracy to that of BP and DGC while enhancing the training speed. Furthermore, networks utilizing DGC maintain a higher level of accuracy than those using BP in the presence of variations in hardware (such as synaptic device conductance and neuron circuit component variations) while requiring fewer circuit components.
{"title":"Direct Gradient Calculation: Simple and Variation‐Tolerant On‐Chip Training Method for Neural Networks","authors":"Hyungyo Kim, Joon Hwang, D. Kwon, Jangsaeng Kim, Min-Kyu Park, Ji-Young Im, Byung-Gook Park, Jong-Ho Lee","doi":"10.1002/aisy.202100064","DOIUrl":"https://doi.org/10.1002/aisy.202100064","url":null,"abstract":"On‐chip training of neural networks (NNs) is regarded as a promising training method for neuromorphic systems with analog synaptic devices. Herein, a novel on‐chip training method called direct gradient calculation (DGC) is proposed to substitute conventional backpropagation (BP). In this method, the gradients of a cost function with respect to the weights are calculated directly by sequentially applying a small temporal change to each weight and then measuring the change in cost value. DGC achieves a similar accuracy to that of BP while performing a handwritten digit classification task, validating its training feasibility. In particular, DGC can be applied to analog hardware‐based convolutional NNs (CNNs), which is considered to be a challenging task, enabling appropriate on‐chip training. A hybrid method is also proposed that efficiently combines DGC and BP for training CNNs, and the method achieves a similar accuracy to that of BP and DGC while enhancing the training speed. Furthermore, networks utilizing DGC maintain a higher level of accuracy than those using BP in the presence of variations in hardware (such as synaptic device conductance and neuron circuit component variations) while requiring fewer circuit components.","PeriodicalId":7187,"journal":{"name":"Advanced Intelligent Systems","volume":"11 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-07-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89587468","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}
V. Ramachandran, Fabian Schilling, A. Wu, D. Floreano
People learn motor activities best when they are conscious of their errors and make a concerted effort to correct them. While haptic interfaces can facilitate motor training, existing interfaces are often bulky and do not always ensure post‐training skill retention. Herein, a programmable haptic sleeve composed of textile‐based electroadhesive clutches for skill acquisition and retention is described. Its functionality in a motor learning study where users control a drone's movement using elbow joint rotation is shown. Haptic feedback is used to restrain elbow motion and make users aware of their errors. This helps users consciously learn to avoid errors from occurring. While all subjects exhibited similar performance during the baseline phase of motor learning, those subjects who received haptic feedback from the haptic sleeve committed 23.5% fewer errors than subjects in the control group during the evaluation phase. The results show that the sleeve helps users retain and transfer motor skills better than visual feedback alone. This work shows the potential for fabric‐based haptic interfaces as a training aid for motor tasks in the fields of rehabilitation and teleoperation.
{"title":"Smart Textiles that Teach: Fabric‐Based Haptic Device Improves the Rate of Motor Learning","authors":"V. Ramachandran, Fabian Schilling, A. Wu, D. Floreano","doi":"10.1002/aisy.202100043","DOIUrl":"https://doi.org/10.1002/aisy.202100043","url":null,"abstract":"People learn motor activities best when they are conscious of their errors and make a concerted effort to correct them. While haptic interfaces can facilitate motor training, existing interfaces are often bulky and do not always ensure post‐training skill retention. Herein, a programmable haptic sleeve composed of textile‐based electroadhesive clutches for skill acquisition and retention is described. Its functionality in a motor learning study where users control a drone's movement using elbow joint rotation is shown. Haptic feedback is used to restrain elbow motion and make users aware of their errors. This helps users consciously learn to avoid errors from occurring. While all subjects exhibited similar performance during the baseline phase of motor learning, those subjects who received haptic feedback from the haptic sleeve committed 23.5% fewer errors than subjects in the control group during the evaluation phase. The results show that the sleeve helps users retain and transfer motor skills better than visual feedback alone. This work shows the potential for fabric‐based haptic interfaces as a training aid for motor tasks in the fields of rehabilitation and teleoperation.","PeriodicalId":7187,"journal":{"name":"Advanced Intelligent Systems","volume":"4 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84281360","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}
The sustainability of ever more sophisticated artificial intelligence relies on the continual development of highly energy‐efficient and compact computing hardware that mimics the biological neural networks. Recently, the neural firing properties have been widely explored in various spiking neuron devices, which could emerge as the fundamental building blocks of future neuromorphic/in‐memory computing hardware. By leveraging the intrinsic device characteristics, the device‐based spiking neuron has the potential advantage of a compact circuit area for implementing neural networks with high density and high parallelism. However, a comprehensive benchmark that considers not only the device but also the peripheral circuit necessary for realizing complete neural functions is still lacking. Herein, the recent progress of emerging spiking neuron devices and circuits is reviewed. By implementing peripheral analog circuits for supporting various spiking neuron devices in the in‐memory computing architecture, the advantages and challenges in area and energy efficiency are discussed by benchmarking various technologies. A small or even no membrane capacitor, a self‐reset property, and a high spiking frequency are highly desirable.
{"title":"Progress and Benchmark of Spiking Neuron Devices and Circuits","authors":"Fu-Xiang Liang, I-Ting Wang, T. Hou","doi":"10.1002/aisy.202100007","DOIUrl":"https://doi.org/10.1002/aisy.202100007","url":null,"abstract":"The sustainability of ever more sophisticated artificial intelligence relies on the continual development of highly energy‐efficient and compact computing hardware that mimics the biological neural networks. Recently, the neural firing properties have been widely explored in various spiking neuron devices, which could emerge as the fundamental building blocks of future neuromorphic/in‐memory computing hardware. By leveraging the intrinsic device characteristics, the device‐based spiking neuron has the potential advantage of a compact circuit area for implementing neural networks with high density and high parallelism. However, a comprehensive benchmark that considers not only the device but also the peripheral circuit necessary for realizing complete neural functions is still lacking. Herein, the recent progress of emerging spiking neuron devices and circuits is reviewed. By implementing peripheral analog circuits for supporting various spiking neuron devices in the in‐memory computing architecture, the advantages and challenges in area and energy efficiency are discussed by benchmarking various technologies. A small or even no membrane capacitor, a self‐reset property, and a high spiking frequency are highly desirable.","PeriodicalId":7187,"journal":{"name":"Advanced Intelligent Systems","volume":"23 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73181130","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}
Reliable image perception is critical for living organisms. Biologic sensory organs and nervous systems evolved interdependently to allow apprehension of visual information regardless of spatial orientation. By contrast, convolutional neural networks usually have limited tolerance to rotational transformations. There are software‐based approaches used to address this issue, such as artificial rotation of training data or preliminary image processing. However, these workarounds require a large computational effort and are mostly done offline. This work presents a bioinspired, robotic vision system with inherent rotation‐invariant properties that may be taught either offline or in real time by feeding back error indications. It is successfully trained to counter the move of a human player in a game of Paper Scissors Stone. The architecture and operation principles are first discussed alongside the experimental setup. This is followed by performance analysis of pattern recognition under misaligned and rotated conditions. Finally, the process of online, supervised learning is demonstrated and analyzed.
{"title":"Bioinspired Robotic Vision with Online Learning Capability and Rotation‐Invariant Properties","authors":"D. Berco, D. Ang","doi":"10.1002/aisy.202100025","DOIUrl":"https://doi.org/10.1002/aisy.202100025","url":null,"abstract":"Reliable image perception is critical for living organisms. Biologic sensory organs and nervous systems evolved interdependently to allow apprehension of visual information regardless of spatial orientation. By contrast, convolutional neural networks usually have limited tolerance to rotational transformations. There are software‐based approaches used to address this issue, such as artificial rotation of training data or preliminary image processing. However, these workarounds require a large computational effort and are mostly done offline. This work presents a bioinspired, robotic vision system with inherent rotation‐invariant properties that may be taught either offline or in real time by feeding back error indications. It is successfully trained to counter the move of a human player in a game of Paper Scissors Stone. The architecture and operation principles are first discussed alongside the experimental setup. This is followed by performance analysis of pattern recognition under misaligned and rotated conditions. Finally, the process of online, supervised learning is demonstrated and analyzed.","PeriodicalId":7187,"journal":{"name":"Advanced Intelligent Systems","volume":"140 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-06-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86590398","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}
Yuyang Ji, Congcong Luan, Xinhua Yao, Jianzhong Fu, Yong He
Recently, considerable achievements have been made with the advancements of smart structures, which are known for their controlled deformation, self‐repair, and sensing characteristics. Such capabilities have significant potential in the field of bionics. 3D printing methods have revolutionized the high‐resolution integrated manufacturing of complex smart structures, resulting in new types of soft robots, actuators, wearable flexible electronics, and biomedical equipment. There is therefore a need for academia and industry to receive an update on the status of these tools. For this reason, herein, a comprehensive overview of the latest progress in printing methods, materials, and applications of various smart structures is provided. Temperature‐ and electromagnetic‐responsive smart structures are highlighted, in addition to self‐healing and smart‐sensing devices. Current exigencies and future development trends of 3D printing methods and smart structures are also summarized.
{"title":"Recent Progress in 3D Printing of Smart Structures: Classification, Challenges, and Trends","authors":"Yuyang Ji, Congcong Luan, Xinhua Yao, Jianzhong Fu, Yong He","doi":"10.1002/aisy.202000271","DOIUrl":"https://doi.org/10.1002/aisy.202000271","url":null,"abstract":"Recently, considerable achievements have been made with the advancements of smart structures, which are known for their controlled deformation, self‐repair, and sensing characteristics. Such capabilities have significant potential in the field of bionics. 3D printing methods have revolutionized the high‐resolution integrated manufacturing of complex smart structures, resulting in new types of soft robots, actuators, wearable flexible electronics, and biomedical equipment. There is therefore a need for academia and industry to receive an update on the status of these tools. For this reason, herein, a comprehensive overview of the latest progress in printing methods, materials, and applications of various smart structures is provided. Temperature‐ and electromagnetic‐responsive smart structures are highlighted, in addition to self‐healing and smart‐sensing devices. Current exigencies and future development trends of 3D printing methods and smart structures are also summarized.","PeriodicalId":7187,"journal":{"name":"Advanced Intelligent Systems","volume":"10 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-05-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90978156","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}
T. Dalgaty, E. Esmanhotto, N. Castellani, D. Querlioz, E. Vianello
Neural networks cannot typically be trained locally in edge‐computing systems due to severe energy constraints. It has, therefore, become commonplace to train them “ex situ” and transfer the resulting model to a dedicated inference hardware. Resistive memory arrays are of particular interest for realizing such inference hardware, because they offer an extremely low‐power implementation of the dot‐product operation. However, the transfer of high‐precision software parameters to the imprecise and random conductance states of resistive memories poses significant challenges. Here, it is proposed that Bayesian neural networks can be more suitable for model transfer, because, such as device conductance states, their parameters are described by random variables. The ex situ training of a Bayesian neural network is performed, and then, the resulting software model is transferred in a single programming step to an array of 16 384 resistive memory devices. On an illustrative classification task, it is observed that the transferred decision boundaries and the prediction uncertainties of the software model are well preserved. This work demonstrates that resistive memory‐based Bayesian neural networks are a promising direction in the development of resistive memory compatible edge inference hardware.
{"title":"Ex Situ Transfer of Bayesian Neural Networks to Resistive Memory‐Based Inference Hardware","authors":"T. Dalgaty, E. Esmanhotto, N. Castellani, D. Querlioz, E. Vianello","doi":"10.1002/aisy.202000103","DOIUrl":"https://doi.org/10.1002/aisy.202000103","url":null,"abstract":"Neural networks cannot typically be trained locally in edge‐computing systems due to severe energy constraints. It has, therefore, become commonplace to train them “ex situ” and transfer the resulting model to a dedicated inference hardware. Resistive memory arrays are of particular interest for realizing such inference hardware, because they offer an extremely low‐power implementation of the dot‐product operation. However, the transfer of high‐precision software parameters to the imprecise and random conductance states of resistive memories poses significant challenges. Here, it is proposed that Bayesian neural networks can be more suitable for model transfer, because, such as device conductance states, their parameters are described by random variables. The ex situ training of a Bayesian neural network is performed, and then, the resulting software model is transferred in a single programming step to an array of 16 384 resistive memory devices. On an illustrative classification task, it is observed that the transferred decision boundaries and the prediction uncertainties of the software model are well preserved. This work demonstrates that resistive memory‐based Bayesian neural networks are a promising direction in the development of resistive memory compatible edge inference hardware.","PeriodicalId":7187,"journal":{"name":"Advanced Intelligent Systems","volume":"95 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80465352","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}
The advances of neural recording techniques have fostered rapid growth of the number of simultaneously recorded neurons, opening up new possibilities to investigate the interactions and dynamics inside neural circuitry. The high recording channel counts, however, pose significant challenges for data analysis because the required time and computational resources grow superlinearly with the data volume. Herein, the feasibility of real‐time reconstruction of neural functional connectivity using a second‐order memristor network is analyzed. Spike‐timing‐dependent plasticity, natively implemented by the internal dynamics of the memristor device, leads to the successful discovery of temporal correlations between pre‐ and postsynaptic spikes of the simulated neural circuits in an unsupervised fashion. The proposed system demonstrates high classification accuracy under a wide range of parameter settings considering indirect connections, synaptic weights, transmission delays, connection density, and so on, and enables the capturing of dynamic connectivity evolutions. The influence of device nonideal factors on detection accuracy is systematically evaluated, and the system shows robustness to initial weight randomness, and cycle‐to‐cycle and device‐to‐device variations. The proposed method allows direct mapping of neural connectivity onto the artificial memristor network and can lead to efficient front‐end data analysis of high‐density neural recording systems and potentially directly coupled bioartificial networks.
{"title":"Neural Functional Connectivity Reconstruction with Second‐Order Memristor Network","authors":"Yuting Wu, John Moon, Xiaojian Zhu, W. Lu","doi":"10.1002/aisy.202000276","DOIUrl":"https://doi.org/10.1002/aisy.202000276","url":null,"abstract":"The advances of neural recording techniques have fostered rapid growth of the number of simultaneously recorded neurons, opening up new possibilities to investigate the interactions and dynamics inside neural circuitry. The high recording channel counts, however, pose significant challenges for data analysis because the required time and computational resources grow superlinearly with the data volume. Herein, the feasibility of real‐time reconstruction of neural functional connectivity using a second‐order memristor network is analyzed. Spike‐timing‐dependent plasticity, natively implemented by the internal dynamics of the memristor device, leads to the successful discovery of temporal correlations between pre‐ and postsynaptic spikes of the simulated neural circuits in an unsupervised fashion. The proposed system demonstrates high classification accuracy under a wide range of parameter settings considering indirect connections, synaptic weights, transmission delays, connection density, and so on, and enables the capturing of dynamic connectivity evolutions. The influence of device nonideal factors on detection accuracy is systematically evaluated, and the system shows robustness to initial weight randomness, and cycle‐to‐cycle and device‐to‐device variations. The proposed method allows direct mapping of neural connectivity onto the artificial memristor network and can lead to efficient front‐end data analysis of high‐density neural recording systems and potentially directly coupled bioartificial networks.","PeriodicalId":7187,"journal":{"name":"Advanced Intelligent Systems","volume":"22 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84542996","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}
Christopher M. Shaffer, Atharva Deo, Andrew Tudor, Rahul Shenoy, Cameron D. Danesh, Dhruva Nathan, Lawren L. Gamble, D. Inman, Yong Chen
Unlike artificial intelligent systems based on computers which have to be programmed for specific tasks, the human brain “self‐programs” in real time to create new tactics and adapt to arbitrary environments. Computers embedded in artificial intelligent systems execute arbitrary signal‐processing algorithms to outperform humans at specific tasks, but without the real‐time self‐programming functionality, they are preprogrammed by humans, fail in unpredictable environments beyond their preprogrammed domains, and lack general intelligence in arbitrary environments. Herein, a synaptic resistor circuit that self‐programs in arbitrary and unpredictable environments in real time is demonstrated. By integrating the synaptic signal processing, memory, and correlative learning functions in each synaptic resistor, the synaptic resistor circuit processes signals and self‐programs the circuit concurrently in real time with an energy efficiency about six orders higher than those of computers. In comparison with humans and a preprogrammed computer, the self‐programming synaptic resistor circuit dynamically modifies its algorithm to control a morphing wing in an unpredictable aerodynamic environment to improve its performance function with superior self‐programming speeds and accuracy. The synaptic resistor circuits potentially circumvent the fundamental limitations of computers, leading to a new intelligent platform with real‐time self‐programming functionality for artificial general intelligence.
{"title":"Self‐Programming Synaptic Resistor Circuit for Intelligent Systems","authors":"Christopher M. Shaffer, Atharva Deo, Andrew Tudor, Rahul Shenoy, Cameron D. Danesh, Dhruva Nathan, Lawren L. Gamble, D. Inman, Yong Chen","doi":"10.1002/aisy.202100016","DOIUrl":"https://doi.org/10.1002/aisy.202100016","url":null,"abstract":"Unlike artificial intelligent systems based on computers which have to be programmed for specific tasks, the human brain “self‐programs” in real time to create new tactics and adapt to arbitrary environments. Computers embedded in artificial intelligent systems execute arbitrary signal‐processing algorithms to outperform humans at specific tasks, but without the real‐time self‐programming functionality, they are preprogrammed by humans, fail in unpredictable environments beyond their preprogrammed domains, and lack general intelligence in arbitrary environments. Herein, a synaptic resistor circuit that self‐programs in arbitrary and unpredictable environments in real time is demonstrated. By integrating the synaptic signal processing, memory, and correlative learning functions in each synaptic resistor, the synaptic resistor circuit processes signals and self‐programs the circuit concurrently in real time with an energy efficiency about six orders higher than those of computers. In comparison with humans and a preprogrammed computer, the self‐programming synaptic resistor circuit dynamically modifies its algorithm to control a morphing wing in an unpredictable aerodynamic environment to improve its performance function with superior self‐programming speeds and accuracy. The synaptic resistor circuits potentially circumvent the fundamental limitations of computers, leading to a new intelligent platform with real‐time self‐programming functionality for artificial general intelligence.","PeriodicalId":7187,"journal":{"name":"Advanced Intelligent Systems","volume":"24 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90378610","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}
Xiaochen Shi, Yan Chen, Hong-Lan Jiang, Du-Li Yu, Xiaoliang Guo
Driving toward the goal of gaining a high level of intelligence and agility that mimics or surpasses that of humans, sensing systems have been widely investigated. As a complex network, tactile sense converts environmental stimuli into electrical impulses through various sensory receptors, which has been exploited in a large number of revolutionary applications, including robotics, prosthetics, and health‐monitoring devices. However, it remains significantly difficult to mimic all the functionalities of human skin. Herein, a machine tactile sensing system is proposed based on machine vision, which is commonly referred to as “electronic skin” or “e‐skin.” With a high density of 625 sensing points per square centimeter similar to that of human skin, the proposed sensing system can successfully measure 3D force and temperature distribution simultaneously. Based on this information, the shape, weight, texture, stiffness, and viscosity of objects can be obtained, comprehensively mimicking the human tactile system. Moreover, the experimental results show that the proposed e‐skin achieves excellent repeatability, reproducibility, and stability compared to those based on other principles such as the piezoresistive effect and capacitive effect.
{"title":"High‐Density Force and Temperature Sensing Skin Using Micropillar Array with Image Sensor","authors":"Xiaochen Shi, Yan Chen, Hong-Lan Jiang, Du-Li Yu, Xiaoliang Guo","doi":"10.1002/aisy.202000280","DOIUrl":"https://doi.org/10.1002/aisy.202000280","url":null,"abstract":"Driving toward the goal of gaining a high level of intelligence and agility that mimics or surpasses that of humans, sensing systems have been widely investigated. As a complex network, tactile sense converts environmental stimuli into electrical impulses through various sensory receptors, which has been exploited in a large number of revolutionary applications, including robotics, prosthetics, and health‐monitoring devices. However, it remains significantly difficult to mimic all the functionalities of human skin. Herein, a machine tactile sensing system is proposed based on machine vision, which is commonly referred to as “electronic skin” or “e‐skin.” With a high density of 625 sensing points per square centimeter similar to that of human skin, the proposed sensing system can successfully measure 3D force and temperature distribution simultaneously. Based on this information, the shape, weight, texture, stiffness, and viscosity of objects can be obtained, comprehensively mimicking the human tactile system. Moreover, the experimental results show that the proposed e‐skin achieves excellent repeatability, reproducibility, and stability compared to those based on other principles such as the piezoresistive effect and capacitive effect.","PeriodicalId":7187,"journal":{"name":"Advanced Intelligent Systems","volume":"55 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86080596","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：