Browsing by Keyword "Artificial Intelligence"
Now showing 1 - 20 of 57
Results Per Page
Sort Options
Item An active adaptation strategy for streaming time series classification based on elastic similarity measures(2022-08) Oregi, Izaskun; Pérez, Aritz; Del Ser, Javier; Lozano, Jose A.; Quantum; IAIn streaming time series classification problems, the goal is to predict the label associated to the most recently received observations over the stream according to a set of categorized reference patterns. In on-line scenarios, data arise from non-stationary processes, which results in a succession of different patterns or events. This work presents an active adaptation strategy that allows time series classifiers to accommodate to the dynamics of streamed time series data. Specifically, our approach consists of a classifier that detects changes between events over streaming time series. For this purpose, the classifier uses features of the dynamic time warping measure computed between the streamed data and a set of reference patterns. When classifying a streaming series, the proposed pattern end detector analyzes such features to predict changes and adapt off-line time series classifiers to newly arriving events. To evaluate the performance of the proposed scheme, we employ the pattern end detection model along with dynamic time warping-based nearest neighbor classifiers over a benchmark of ten time series classification problems. The obtained results present exciting insights into the detection accuracy and latency performance of the proposed strategy.Item Aggregate Farming in the Cloud: The AFarCloud ECSEL project: The AFarCloud ECSEL project(2020-10) Castillejo, Pedro; Johansen, Gorm; Cürüklü, Baran; Bilbao-Arechabala, Sonia; Fresco, Roberto; Martinez-Rodriguez, Belen; Pomante, Luigi; Rusu, Cristina; Martínez-Ortega, José-Fernán; Centofanti, Carlo; Hakojärvi, Mikko; Santic, Marco; Häggman, Johanna; Tecnalia Research & Innovation; BIGDATAFarming is facing many economic challenges in terms of productivity and cost-effectiveness. Labor shortage partly due to depopulation of rural areas, especially in Europe, is another challenge. Domain specific problems such as accurate monitoring of soil and crop properties and animal health are key factors for minimizing economical risks, and not risking human health. The ECSEL AFarCloud (Aggregate Farming in the Cloud) project will provide a distributed platform for autonomous farming that will allow the integration and cooperation of agriculture Cyber Physical Systems in real-time in order to increase efficiency, productivity, animal health, food quality and reduce farm labor costs. Moreover, such a platform can be integrated with farm management software to support monitoring and decision-making solutions based on big data and real-time data mining techniques.Item AI-based medical e-diagnosis for fast and automatic ventricular volume measurement in patients with normal pressure hydrocephalus(2022-02-24) Zhou, Xi; Ye, Qinghao; Yang, Xiaolin; Chen, Jiakun; Ma, Haiqin; Xia, Jun; Del Ser, Javier; Yang, Guang; IABased on CT and MRI images acquired from normal pressure hydrocephalus (NPH) patients, using machine learning methods, we aim to establish a multimodal and high-performance automatic ventricle segmentation method to achieve an efficient and accurate automatic measurement of the ventricular volume. First, we extract the brain CT and MRI images of 143 definite NPH patients. Second, we manually label the ventricular volume (VV) and intracranial volume (ICV). Then, we use the machine learning method to extract features and establish automatic ventricle segmentation model. Finally, we verify the reliability of the model and achieved automatic measurement of VV and ICV. In CT images, the Dice similarity coefficient (DSC), intraclass correlation coefficient (ICC), Pearson correlation, and Bland–Altman analysis of the automatic and manual segmentation result of the VV were 0.95, 0.99, 0.99, and 4.2 ± 2.6, respectively. The results of ICV were 0.96, 0.99, 0.99, and 6.0 ± 3.8, respectively. The whole process takes 3.4 ± 0.3 s. In MRI images, the DSC, ICC, Pearson correlation, and Bland–Altman analysis of the automatic and manual segmentation result of the VV were 0.94, 0.99, 0.99, and 2.0 ± 0.6, respectively. The results of ICV were 0.93, 0.99, 0.99, and 7.9 ± 3.8, respectively. The whole process took 1.9 ± 0.1 s. We have established a multimodal and high-performance automatic ventricle segmentation method to achieve efficient and accurate automatic measurement of the ventricular volume of NPH patients. This can help clinicians quickly and accurately understand the situation of NPH patient’s ventricles.Item Analysis of Alloy 718 surfaces milled by abrasive waterjet and post-processed by plain waterjet technology(2017) Alberdi, A.; Rivero, A.; Artaza, T.; Lamikiz, A.; FABRIC_INTEL; SGThis work analyzes the surfaces obtained in Alloy 718 when they are milled by Abrasive Waterjet (AWJ) at different conditions. This analysis revealed that all surfaces have a homogeneous roughness in the transversal and the longitudinal directions, present embedded abrasive particles and have hardened about 50% with respect to the untreated bulk Alloy 718. On the other hand, Plain Waterjet (PWJ) technology was used for removing the abrasive particles embedded in surfaces of Alloy 718 milled previously by AWJ technology. The effect of this process on the surface characteristics is also analyzed. For all tested conditions, this technology removed all the particles embedded in the surface. In addition, the PWJ technology process in general smoothened the surfaces produced by AWJ milling and it also released near-surface stresses.Item The AQUAS ECSEL Project Aggregated Quality Assurance for Systems: Co-Engineering Inside and Across the Product Life Cycle: Co-Engineering Inside and Across the Product Life Cycle(2019-09) Pomante, Luigi; Muttillo, Vittoriano; Křena, Bohuslav; Vojnar, Tomáš; Veljković, Filip; Magnin, Pacôme; Matschnig, Martin; Fischer, Bernhard; Martinez, Jabier; Gruber, Thomas; SWTThere is an ever-increasing complexity of the systems we engineer in modern society, which includes facing the convergence of the embedded world and the open world. This complexity creates increasing difficulty with providing assurance for factors including safety, security and performance. In such a context, the AQUAS project investigates the challenges arising from e.g., the inter-dependence of safety, security and performance of systems and aims at efficient solutions for the entire product life-cycle. The project builds on knowledge of partners gained in current or former EU projects and will demonstrate the newly developed methods and techniques for co-engineering across use cases spanning Aerospace, Medicine, Transport and Industrial Control.Item Artificial Intelligence, Cybercities and Technosocieties(2017-09-01) Echeverría, Javier; Tabarés, Raúl; BIGDATAInformation technologies have made possible the rising of new forms of communities, cities and societies. These changes are analyzed from the perspective of innovation studies, as technological but also social innovations. Starting from the contributions of Ortega y Gasset to the philosophy of technology, and applying these ideas to the information and communications technologies (ICT) system, this article introduces the notions of technosocieties and cybercities. Our aim is to deeply examine the Telepolis project; a digital and global city supported by ICT and artificial intelligence (AI). We pay attention to the different challenges that AI will have to face in upcoming years in technosocieties and cybercities. In our opinion, the future of AI is tightly related with the technological support of this kind of new city and their cybercitizens. Finally, we claim that there won’t be a shared public space in the infosphere till public organizations acknowledge the importance of promoting and maintaining this new and already needed digital agora.Item Battery Storage Demonstration Projects An Overview Across Europe(Institute of Electrical and Electronics Engineers Inc., 2021) Astero, Poria; Maki, Kari; Evens, Corentin; Papadimitriou, Christina; Efthymiou, Venizelos; Niebe, Astrid; Holly, Stefanie; Marinelli, Mattia; Gabderakhmanova, Tatiana; Melendez, Joaquim; Herraiz, Sergio; Rodriguez-Sanchez, Raul; Morch, Andrei; De Urtasun, Laura Gimenez; Fernandez, Gregorio; Divshali, Poria Hasanpor; Tecnalia Research & InnovationThis paper summarises results and experiences from several demonstration projects across European countries in the field of battery energy storage system (BESS) integration to the power system. These research projects are selected among research institutes and universities that are part of the European Energy Research Alliance (EERA) Joint Program on Smart Grids. The paper categorizes these projects according to the demonstrated applications of BESS and then reviews specific aspects of each project. This paper provides an opportunity to find out the summary of the most recent results as well as challenges and open research questions in projects focusing on different BESS application in the power system.Item Bio-inspired computation for big data fusion, storage, processing, learning and visualization: state of the art and future directions: state of the art and future directions(2021-08-03) Torre-Bastida, Ana I.; Díaz-de-Arcaya, Josu; Osaba, Eneko; Muhammad, Khan; Camacho, David; Del Ser, Javier; HPA; QuantumThis overview gravitates on research achievements that have recently emerged from the confluence between Big Data technologies and bio-inspired computation. A manifold of reasons can be identified for the profitable synergy between these two paradigms, all rooted on the adaptability, intelligence and robustness that biologically inspired principles can provide to technologies aimed to manage, retrieve, fuse and process Big Data efficiently. We delve into this research field by first analyzing in depth the existing literature, with a focus on advances reported in the last few years. This prior literature analysis is complemented by an identification of the new trends and open challenges in Big Data that remain unsolved to date, and that can be effectively addressed by bio-inspired algorithms. As a second contribution, this work elaborates on how bio-inspired algorithms need to be adapted for their use in a Big Data context, in which data fusion becomes crucial as a previous step to allow processing and mining several and potentially heterogeneous data sources. This analysis allows exploring and comparing the scope and efficiency of existing approaches across different problems and domains, with the purpose of identifying new potential applications and research niches. Finally, this survey highlights open issues that remain unsolved to date in this research avenue, alongside a prescription of recommendations for future research.Item A cognitive robotic ecology approach to self-configuring and evolving AAL systems(2015-10-01) Dragone, Mauro; Amato, Giuseppe; Bacciu, Davide; Chessa, Stefano; Coleman, Sonya; Di Rocco, Maurizio; Gallicchio, Claudio; Gennaro, Claudio; Lozano, Hector; Maguire, Liam; McGinnity, Martin; Micheli, Alessio; O׳Hare, Gregory M.P.; Renteria, Arantxa; Saffiotti, Alessandro; Vairo, Claudio; Vance, P.; O'Hare, Gregory M.P.; Medical Technologies; Robótica MédicaRobotic ecologies are systems made out of several robotic devices, including mobile robots, wireless sensors and effectors embedded in everyday environments, where they cooperate to achieve complex tasks. This paper demonstrates how endowing robotic ecologies with information processing algorithms such as perception, learning, planning, and novelty detection can make these systems able to deliver modular, flexible, manageable and dependable Ambient Assisted Living (AAL) solutions. Specifically, we show how the integrated and self-organising cognitive solutions implemented within the EU project RUBICON (Robotic UBIquitous Cognitive Network) can reduce the need of costly pre-programming and maintenance of robotic ecologies. We illustrate how these solutions can be harnessed to (i) deliver a range of assistive services by coordinating the sensing & acting capabilities of heterogeneous devices, (ii) adapt and tune the overall behaviour of the ecology to the preferences and behaviour of its inhabitants, and also (iii) deal with novel events, due to the occurrence of new user's activities and changing user's habits.Item Collaborative Robots in e-waste Management(2017) Alvarez-de-los-Mozos, Esther; Renteria, Arantxa; Robótica MédicaNowadays manufacturing companies are going through an increasing public and government pressure to reduce the environmental impact of their operations. But when dealing with e-waste, some difficulties arise in classifying and dismantling electronic devices. Manual operations are financially prohibitive and full automation is also discarded due to the lack of uniformity of the disposed devices. A halfway solution is to let a human operator and a robot share the process. The goal of this research is the optimization of the recycling process of electronic equipments, applying both technical and economic criteria, and taking into account the latest developments in collaborative robots.Item Consistent arm rehabilitation from clinical to home environment - Integrating the universal haptic drive into the TeleReha software platform(Springer International Publishing, 2013) Veneman, Jan F.; Jung, Je Hyung; Perry, Joel C.; Keller, Thierry; Tecnalia Research & Innovation; Medical TechnologiesThis paper describes the current work on integrating a haptic force feedback device, named the Universal Haptic Drive (UHD), for upper limb training into a software platform for telerehabilitation which has been developed for at-home rehabilitation after stroke. The aim of the integration is to provide a consistent training and assessment platform during the entire rehabilitation period, from clinical facilities to home, while also allowing less specialized supervision to rehabilitate a stroke patient.Item Deep convolutional neural network for damaged vegetation segmentation from RGB images based on virtual NIR-channel estimation(2022-01) Picon, Artzai; Bereciartua-Perez, Arantza; Eguskiza, Itziar; Romero-Rodriguez, Javier; Jimenez-Ruiz, Carlos Javier; Eggers, Till; Klukas, Christian; Navarra-Mestre, Ramon; COMPUTER_VISIONPerforming accurate and automated semantic segmentation of vegetation is a first algorithmic step towards more complex models that can extract accurate biological information on crop health, weed presence and phenological state, among others. Traditionally, models based on normalized difference vegetation index (NDVI), near infrared channel (NIR) or RGB have been a good indicator of vegetation presence. However, these methods are not suitable for accurately segmenting vegetation showing damage, which precludes their use for downstream phenotyping algorithms. In this paper, we propose a comprehensive method for robust vegetation segmentation in RGB images that can cope with damaged vegetation. The method consists of a first regression convolutional neural network to estimate a virtual NIR channel from an RGB image. Second, we compute two newly proposed vegetation indices from this estimated virtual NIR: the infrared-dark channel subtraction (IDCS) and infrared-dark channel ratio (IDCR) indices. Finally, both the RGB image and the estimated indices are fed into a semantic segmentation deep convolutional neural network to train a model to segment vegetation regardless of damage or condition. The model was tested on 84 plots containing thirteen vegetation species showing different degrees of damage and acquired over 28 days. The results show that the best segmentation is obtained when the input image is augmented with the proposed virtual NIR channel (F1=0.94) and with the proposed IDCR and IDCS vegetation indices (F1=0.95) derived from the estimated NIR channel, while the use of only the image or RGB indices lead to inferior performance (RGB(F1=0.90) NIR(F1=0.82) or NDVI(F1=0.89) channel). The proposed method provides an end-to-end land cover map segmentation method directly from simple RGB images and has been successfully validated in real field conditions.Item Deep learning to find colorectal polyps in colonoscopy: A systematic literature review: A systematic literature review(2020-08) Sánchez-Peralta, Luisa F.; Bote-Curiel, Luis; Picón, Artzai; Sánchez-Margallo, Francisco M.; Pagador, J. Blas; COMPUTER_VISIONColorectal cancer has a great incidence rate worldwide, but its early detection significantly increases the survival rate. Colonoscopy is the gold standard procedure for diagnosis and removal of colorectal lesions with potential to evolve into cancer and computer-aided detection systems can help gastroenterologists to increase the adenoma detection rate, one of the main indicators for colonoscopy quality and predictor for colorectal cancer prevention. The recent success of deep learning approaches in computer vision has also reached this field and has boosted the number of proposed methods for polyp detection, localization and segmentation. Through a systematic search, 35 works have been retrieved. The current systematic review provides an analysis of these methods, stating advantages and disadvantages for the different categories used; comments seven publicly available datasets of colonoscopy images; analyses the metrics used for reporting and identifies future challenges and recommendations. Convolutional neural networks are the most used architecture together with an important presence of data augmentation strategies, mainly based on image transformations and the use of patches. End-to-end methods are preferred over hybrid methods, with a rising tendency. As for detection and localization tasks, the most used metric for reporting is the recall, while Intersection over Union is highly used in segmentation. One of the major concerns is the difficulty for a fair comparison and reproducibility of methods. Even despite the organization of challenges, there is still a need for a common validation framework based on a large, annotated and publicly available database, which also includes the most convenient metrics to report results. Finally, it is also important to highlight that efforts should be focused in the future on proving the clinical value of the deep learning based methods, by increasing the adenoma detection rate.Item Design and integration of WAAM technology and in situ monitoring system in a gantry machine(2017) Artaza, T.; Alberdi, A.; Murua, M.; Gorrotxategi, J.; Frías, J.; Puertas, G.; Melchor, M.A.; Mugica, D.; Suárez, A.; FABRIC_INTEL; FACTORY; ROBOTICA_AUTOMA; Tecnalia Research & Innovation; VISUALWire arc additive manufacturing, WAAM, is a popular wire-feed additive manufacturing technology that creates components through the deposition of material layer-by-layer. WAAM has become a promising alternative to conventional machining due to its high deposition rate, environmental friendliness and cost-competitiveness. In this research work, an adaptation of a gantry machine with in-situ monitoring and a control system has been carried out, in order to expose the ability of the WAAM technology to fabricate complex-shaped parts. The retrofitting of the machine has been done in several layers called respectively hardware, control and software layers. For the validation of the implemented system, a stainless steel 316L demonstrator has been manufactured, and the required stages have been employed, including part design (CAD), process parameters selection, tool-path definition (CAM) and part manufacturing. This study has shown the feasibility of the adapted machine for additive manufacturing as a controlled process.Item Designing a generalised reward for Building Energy Management Reinforcement Learning agents(IEEE, 2021-09-08) Martinez, Ruben Mulero; Goikolea, Benat Arregi; Beitia, Inigo Mendialdua; Martinez, Roberto Garay; Mulero, Rubén; Arregi, Beñat; Mendialdua, Iñigo; Garay, Roberto; Solic, Petar; Nizetic, Sandro; Rodrigues, Joel J. P. C.; Rodrigues, Joel J.P.C.; Gonzalez-de-Artaza, Diego Lopez-de-Ipina; Perkovic, Toni; Catarinucci, Luca; Patrono, Luigi; DIGITALIZACIÓN Y AUTOMATIZACIÓN DE LA CONSTRUCCIÓN; EDIFICACIÓN DE ENERGÍA POSITIVA; Tecnalia Research & InnovationThe reduction of the carbon footprint of buildings is a challenging task, partly due to the conflicting goals of maximising occupant comfort and minimising energy consumption. An intelligent management of Heating, Ventilation and Air Conditioning (HVAC) systems is creating a promising research line in which the creation of suitable algorithms could reduce energy consumption maintaining occupants' comfort. In this regard, Reinforcement Learning (RL) approaches are giving a good balance between data requirements and intelligent operations to control building systems. However, there is a gap concerning how to create a generalised reward signal that can train RL agents without delimiting the problem to a specific or controlled scenario. To tackle it, an analysis and discussion is presented about the necessary requirements for the creation of generalist rewards, with the objective of laying the foundations that allow the creation of generalist intelligent agents for building energy management.Item Driver Monitoring System Based on CNN Models: An Approach for Attention Level Detection: An Approach for Attention Level Detection(Springer, 2020-10-27) Vaca-Recalde, Myriam E.; Pérez, Joshué; Echanobe, Javier; Analide, Cesar; Novais, Paulo; Camacho, David; Yin, Hujun; CCAMDrivers provide a wide range of focus characteristics that can evaluate their attention level and analyze their behavioral states while driving. This information is critical for the development of new automated driving functionalities that support and assist the driver according to his/her state, ensuring safety for them and other users on the road. In this sense, this paper proposes a Driver Monitoring System (DMS) based on image processing and Convolutional Neural Networks (CNN), that analyzes two important driver distraction aspects: inattention of the road and drowsiness. Our approach makes use of CNN models for detecting the gaze and the head direction, which involves training datasets with different pre-defined labels. Additionally, the system is complemented with the drowsiness level measurement, using face features to detect the time that the eyes are closed or opened, and the blinking rate. Crossing the inference results of these models, the system can provide an accurate estimation of driver attention level. The different parts of the presented DMS have been trained in a Hardware-in-the-loop driving simulator with an eye fish camera. It has been tested as a real-time application recording driver with different characteristics.Item Edge-enhanced dual discriminator generative adversarial network for fast MRI with parallel imaging using multi-view information(2022-01-28) Huang, Jiahao; Ding, Weiping; Lv, Jun; Yang, Jingwen; Dong, Hao; Del Ser, Javier; Xia, Jun; Ren, Tiaojuan; Wong, Stephen T.; Yang, Guang; IAIn clinical medicine, magnetic resonance imaging (MRI) is one of the most important tools for diagnosis, triage, prognosis, and treatment planning. However, MRI suffers from an inherent slow data acquisition process because data is collected sequentially in k-space. In recent years, most MRI reconstruction methods proposed in the literature focus on holistic image reconstruction rather than enhancing the edge information. This work steps aside this general trend by elaborating on the enhancement of edge information. Specifically, we introduce a novel parallel imaging coupled dual discriminator generative adversarial network (PIDD-GAN) for fast multi-channel MRI reconstruction by incorporating multi-view information. The dual discriminator design aims to improve the edge information in MRI reconstruction. One discriminator is used for holistic image reconstruction, whereas the other one is responsible for enhancing edge information. An improved U-Net with local and global residual learning is proposed for the generator. Frequency channel attention blocks (FCA Blocks) are embedded in the generator for incorporating attention mechanisms. Content loss is introduced to train the generator for better reconstruction quality. We performed comprehensive experiments on Calgary-Campinas public brain MR dataset and compared our method with state-of-the-art MRI reconstruction methods. Ablation studies of residual learning were conducted on the MICCAI13 dataset to validate the proposed modules. Results show that our PIDD-GAN provides high-quality reconstructed MR images, with well-preserved edge information. The time of single-image reconstruction is below 5ms, which meets the demand of faster processing.Item Effects of the Nozzle Tip Clogging and the Scanning Direction on the Deposition Process During Laser Metal Deposition of Alloy 718 Using a Four-Stream Discrete Nozzle(2019) Artaza, Teresa; Ramiro, Pedro; Ortiz, Mikel; Alberdi, Amaia; Lamikiz, Aitzol; FABRIC_INTELDepending on the configuration of the LMD system, the nozzle tilting is necessary to be able to manufacture parts with complex geometry. In these cases, the use of discrete coaxial nozzles is recommended. With this type of nozzle, the powder can clog the internal tips of the nozzle streams due to an inappropriate shape, size distribution, humidity or temperature conditions of the powder particles during the deposition process. This undesired effect can be an opportunity depending on the combination of the activated powder tips for coating complex surfaces when the geometry of the substrate acts as a barrier for the powder stream. This work presents for first time the effect of the scanning direction and the stream clogging on the deposition process in terms of powder efficiency, Material Deposition Rate (MDR) and clad geometry and dimensions, when Alloy 718 is deposited by LMD using a four-stream discrete coaxial nozzle.Item An energy efficient intelligent torque vectoring approach based on fuzzy logic controller and neural network tire forces estimator(2021-01-13) Parra, Alberto; Zubizarreta, Asier; Pérez, Joshué; Tecnalia Research & Innovation; CCAMIn electric vehicles (EVs) with multiple motors, torque vectoring (TV) control can effectively enhance the cornering response and safety. Moreover, TV systems can also improve the overall efficiency through an optimal torque distribution that also considers the power consumption. For such a complex control system with multiple objectives, intelligent control techniques have demonstrated to be one of the best alternatives. However, the works proposed in the literature do not handle both vehicle dynamics behavior and energy efficiency, and generally do not consider the real-time implementability of the developed controllers. To overcome the aforementioned isues, in this work, a novel torque vectoring approach is proposed, which uses a neural network-based vertical tire forces estimator and considers the regenerative braking capabilities of EVs. Moreover, the implementability of the controller in a heterogenous (FPGA and microcontroller) automotive suitable system on chip is addressed, ensuring its real-time capabilities. For the sake of validating the proposed approach, a set of experiments have been carried out in a hardware in the loop setup. The performance of the proposed TV approach has been compared with other two TV approaches from the literature, evaluating them in several challenging manoeuvres in high and low tire-road friction coefficient scenarios. Results show that the proposed approach not only is able to enhance the vehicle dynamics behavior but also to decrease the energy consumption about 13%.Item Evolving Spiking Neural Networks for online learning over drifting data streams(2018-12) Lobo, Jesus L.; Laña, Ibai; Del Ser, Javier; Bilbao, Miren Nekane; Kasabov, Nikola; IANowadays huge volumes of data are produced in the form of fast streams, which are further affected by non-stationary phenomena. The resulting lack of stationarity in the distribution of the produced data calls for efficient and scalable algorithms for online analysis capable of adapting to such changes (concept drift). The online learning field has lately turned its focus on this challenging scenario, by designing incremental learning algorithms that avoid becoming obsolete after a concept drift occurs. Despite the noted activity in the literature, a need for new efficient and scalable algorithms that adapt to the drift still prevails as a research topic deserving further effort. Surprisingly, Spiking Neural Networks, one of the major exponents of the third generation of artificial neural networks, have not been thoroughly studied as an online learning approach, even though they are naturally suited to easily and quickly adapting to changing environments. This work covers this research gap by adapting Spiking Neural Networks to meet the processing requirements that online learning scenarios impose. In particular the work focuses on limiting the size of the neuron repository and making the most of this limited size by resorting to data reduction techniques. Experiments with synthetic and real data sets are discussed, leading to the empirically validated assertion that, by virtue of a tailored exploitation of the neuron repository, Spiking Neural Networks adapt better to drifts, obtaining higher accuracy scores than naive versions of Spiking Neural Networks for online learning environments.
- «
- 1 (current)
- 2
- 3
- »