Tensorflow: A system for large-scale machine learning, 12th {USENIX} Symposium, pp.265-283, 2016. ,
Maskconnect: Connectivity learning by gradient descent, Proceedings of the European Conference on Computer Vision (ECCV), pp.349-365, 2018. ,
N2N learning: Network to network compression via policy gradient reinforcement learning, 6th International Conference on Learning Representations, ICLR, 2018. ,
Evolving the topology of large scale deep neural networks, 21st European Conference on Genetic Programming EuroGP, vol.10781, pp.19-34, 2018. ,
Denser: deep evolutionary network structured representation. Genetic Programming and Evolvable Machines, vol.20, pp.5-35, 2019. ,
S-caffe: Co-designing MPI runtimes and caffe for scalable deep learning on modern GPU clusters, ACM SIGPLAN Symp. on Principles and Practice of Parallel Programming, pp.193-205, 2017. ,
Designing neural network architectures using reinforcement learning, 5th International Conference on Learning Representations ICLR, 2017. ,
Accelerating neural architecture search using performance prediction, 6th International Conference on Learning Representations ICLR, 2018. ,
High-performance simulation-based optimization, Studies in Computational Intelligence, vol.833, 2020. ,
URL : https://hal.archives-ouvertes.fr/hal-02304686
Evolving memory cell structures for sequence learning, 19th International Conference Artificial Neural Networks ICANN'2009, vol.5769, pp.755-764, 2009. ,
Demystifying parallel and distributed deep learning: An in-depth concurrency analysis, ACM Comput. Surv, vol.52, issue.4, 2019. ,
Understanding and simplifying one-shot architecture search, 35th International Conference on Machine Learning ICML, pp.549-558, 2018. ,
Algorithms for hyper-parameter optimization, 25th Annual Conference on Neural Information Processing Systems, pp.2546-2554, 2011. ,
URL : https://hal.archives-ouvertes.fr/hal-00642998
Making a science of model search: Hyperparameter optimization in hundreds of dimensions for vision architectures, 2013. ,
Random search for hyper-parameter optimization, Journal of machine learning research, vol.13, pp.281-305, 2012. ,
Universal representations: The missing link between faces, text, planktons, and cat breeds, 2017. ,
Resampling methods for meta-model validation with recommendations for evolutionary computation, Evolutionary Computation, vol.20, issue.2, pp.249-275, 2012. ,
What is the state of neural network pruning?, 2020. ,
Weight uncertainty in neural network, Proceedings of the 32nd International Conference on Machine Learning ICML, vol.37, pp.1613-1622, 2015. ,
Smash: one-shot model architecture search through hypernetworks, 6th International Conference on Learning Representations, ICLR, 2018. ,
Diversity creation methods: a survey and categorisation, Information Fusion, vol.6, issue.1, pp.5-20, 2005. ,
Deepswarm: optimising convolutional neural networks using swarm intelligence, Advances in Computational Intelligence Systems, pp.119-130, 2019. ,
, Predict and deploy energy-efficient convolutional neural networks, 2017.
Efficient architecture search by network transformation, Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence (AAAI-18), pp.2787-2794, 2018. ,
Path-level network transformation for efficient architecture search, Int. Conf. on Machine Learning ICML, pp.677-686, 2018. ,
Bayesian neural architecture search using a training-free performance metric, 2020. ,
Learnable embedding space for efficient neural architecture compression, 7th International Conference on Learning Representations ICLR'2019, 2019. ,
Probabilistic neural architecture search, 2019. ,
Ensemble learning using multi-objective evolutionary algorithms, J. Math. Model. Algorithms, vol.5, issue.4, pp.417-445, 2006. ,
Constraint-aware deep neural network compression, Proceedings of the European Conference on Computer Vision (ECCV), pp.400-415, 2018. ,
Searching for efficient multi-scale architectures for dense image prediction, NIPS, pp.8699-8710, 2018. ,
Net2net: accelerating learning via knowledge transfer, 4th International Conference on Learning Representations, ICLR, 2016. ,
Automatic design of convolutional neural network for hyperspectral image classification, IEEE Trans. Geoscience and Remote Sensing, vol.57, issue.9, pp.7048-7066, 2019. ,
A downsampled variant of imagenet as an alternative to the cifar datasets, 2017. ,
Deep learning with COTS HPC systems, Proceedings of the 30th International Conference on Machine Learning ICML'2013, pp.1337-1345, 2013. ,
, , 2014.
Coevolution of generative adversarial networks, Evoapplications Int. Conf. on Applications of Evolutionary Computation, vol.11454, pp.473-487 ,
Binaryconnect: Training deep neural networks with binary weights during propagations, Advances in Neural Information Processing Systems, pp.3123-3131, 2015. ,
Geeps: scalable deep learning on distributed gpus with a gpu-specialized parameter server, European Conf. on Computer Systems EuroSys'2016, pp.1-16, 2016. ,
A survey of swarm and evolutionary computing approaches for deep learning, Artificial Intelligence Review, vol.53, issue.3, pp.1767-1812, 2020. ,
Deep auto-encoder based multi-task learning using probabilistic transcriptions, 18th Conf. of the International Speech Communication Association, pp.2073-2077, 2017. ,
Large scale distributed deep networks, Advances in neural information processing systems, pp.1223-1231, 2012. ,
Evolving deep recurrent neural networks using ant colony optimization, 15th European Conf. Evolutionary Computation in Combinatorial Optimization EvoCOP'2015, pp.86-98, 2015. ,
Evolutionary parallel extreme learning machines for the data classification problem, Computers & Industrial Engineering, vol.130, pp.237-249, 2019. ,
Speeding up automatic hyperparameter optimization of deep neural networks by extrapolation of learning curves, Int. Joint Conf. on Artificial Intelligence, 2015. ,
Dpp-net: device-aware progressive search for pareto-optimal neural architectures, 15th European Conf. on Computer Vision ECCV, pp.540-555, 2018. ,
Aluminum: An asynchronous, GPU-aware communication library optimized for large-scale training of deep neural networks on HPC systems, vol.00, p.31, 2018. ,
Optimizing long short-term memory recurrent neural networks using ant colony optimization to predict turbine engine vibration, Applied Soft Computing, vol.73, pp.969-991, 2018. ,
Efficient multi-objective neural architecture search via lamarckian evolution, 2018. ,
Simple and efficient architecture search for convolutional neural networks, 6th International Conference on Learning Representations ICLR, 2018. ,
Neural architecture search: A survey, J. Mach. Learn. Res, vol.20, issue.21, pp.1-55, 2019. ,
Blackboard systems, 1988. ,
Bohb: Robust and efficient hyperparameter optimization at scale, Proceedings of the 35th International Conference on Machine Learning ICML, pp.1436-1445, 2018. ,
Computer vision algorithms and hardware implementations: A survey, Integration VLSI journal, vol.69, pp.309-320, 2019. ,
, Evolution channels gradient descent in super neural networks, 2017.
Hyperparameter optimization, Automated Machine Learning, pp.3-33, 2019. ,
Evolving image classification architectures with enhanced particle swarm optimisation, IEEE Access, vol.6, pp.68560-68575, 2018. ,
How meta-heuristic algorithms contribute to deep learning in the hype of big data analytics, Progress in Intelligent Computing Techniques, pp.3-25, 2018. ,
Weight agnostic neural networks, Advances in Neural Information Processing Systems NeurIPS'2019, pp.5365-5379, 2019. ,
Understanding the difficulty of training deep feedforward neural networks, Proceedings of the thirteenth international conference on artificial intelligence and statistics, pp.249-256, 2010. ,
Google vizier: a service for black-box optimization, ACM SIGKDD Int. Conf. on Knowledge Discovery and Data Mining, pp.1487-1495, 2017. ,
A comparison of loss weighting strategies for multi task learning in deep neural networks, IEEE Access, vol.7, pp.141627-141632, 2019. ,
Deep learning, 2016. ,
Generative adversarial nets, Advances in Neural Information Processing Systems NIPS, pp.2672-2680, 2014. ,
, large minibatch sgd: Training imagenet in 1 hour, 2017.
Genetic synthesis of modular neural networks, Proceedings of the 5th International Conference on Genetic Algorithms, pp.318-325, 1993. ,
Learning both weights and connections for efficient neural network, Advances in Neural Information Processing Systems, pp.1135-1143, 2015. ,
Cnn-merp: An FPGA-based memory-efficient reconfigurable processor for forward and backward propagation of convolutional neural networks, 34th Int. Conf. on Computer Design (ICCD'2016), pp.320-327, 2016. ,
, Pipedream: Fast and efficient pipeline parallel dnn training, 2018.
Deep residual learning for image recognition, Proceedings of the IEEE conference on computer vision and pattern recognition, pp.770-778, 2016. ,
Designing neural network hardware accelerators with decoupled objective evaluations, NIPS workshop on Bayesian Optimization, 2016. ,
Predictive entropy search for efficient global optimization of black-box functions, Advances in neural information processing systems, pp.918-926, 2014. ,
A fast learning algorithm for deep belief nets, Neural computation, vol.18, issue.7, pp.1527-1554, 2006. ,
A practical guide to training restricted boltzmann machines, Neural networks: Tricks of the trade, vol.7700, pp.599-619, 2012. ,
A fast learning algorithm for deep belief nets, Neural Computation, vol.18, issue.7, pp.1527-1554, 2006. ,
Speeding up the hyperparameter optimization of deep convolutional neural networks, Int. Journal of Computational Intelligence and Applications, vol.17, issue.02, 2018. ,
Long short-term memory, Neural Computation, vol.9, issue.8, pp.1735-1780 ,
, Monas: Multi-objective neural architecture search using reinforcement learning, 2018.
Densely connected convolutional networks, IEEE Conf. on Computer Vision and Pattern Recognition, pp.4700-4708, 2017. ,
Gpipe: Efficient training of giant neural networks using pipeline parallelism, Advances in Neural Information Processing Systems, pp.103-112, 2019. ,
Automated Machine Learning, 2019. ,
, Cost-aware multi-objective optimization of deep neural networks. arXiv, 2020.
Firecaffe: near-linear acceleration of deep neural network training on compute clusters, IEEE Conf. on Computer Vision and Pattern Recognition, pp.2592-2600, 2016. ,
Efficient hyperparameter optimization for deep learning algorithms using deterministic RBF surrogates, AAAI Conf. on Artificial Intelligence, 2017. ,
Reinforcement learning for neural architecture search: A review, Image and Vision Computing, vol.89, pp.57-66, 2019. ,
Bayesian optimization with tree-structured dependencies, Proceedings of the 34th International Conference on Machine Learning ICML'2017, pp.1655-1664, 2017. ,
Efficient network architecture search via multiobjective particle swarm optimization based on decomposition, Neural Networks, vol.123, pp.305-316, 2020. ,
Auto-keras: An efficient neural architecture search system, Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp.1946-1956, 2019. ,
Surrogate-assisted evolutionary computation: Recent advances and future challenges, Swarm and Evolutionary Computation, vol.1, pp.61-70, 2011. ,
Evolutionary algorithms, fitness landscapes and search, 1995. ,
An empirical exploration of recurrent network architectures, Proceedings of the 32nd International Conference on Machine Learning ICML, pp.2342-2350, 2015. ,
Particle swarm optimization of deep neural networks architectures for image classification, Swarm and Evolutionary Computation, vol.49, pp.62-74, 2019. ,
One model to learn them all, 2017. ,
Neural architecture search with bayesian optimisation and optimal transport, Advances in Neural Information Processing Systems, pp.2016-2025, 2018. ,
Multi-task learning using uncertainty to weigh losses for scene geometry and semantics, IEEE Conf. on Computer Vision and Pattern Recognition CVPR, pp.7482-7491, 2018. ,
Nemo: Neuro-evolution with multiobjective optimization of deep neural network for speed and accuracy ,
Fast bayesian optimization of machine learning hyperparameters on large datasets, Int. Conf. on Artificial Intelligence and Statistics, pp.528-536, 2017. ,
One weird trick for parallelizing convolutional neural networks. CoRR, abs/1404, vol.5997, 2014. ,
Imagenet classification with deep convolutional neural networks, Advances in Neural Information Processing Systems, pp.1106-1114, 2012. ,
Random search and reproducibility for neural architecture search, 2019. ,
Hyperband: A novel bandit-based approach to hyperparameter optimization, Journal of Machine Learning Research, vol.18, issue.1, pp.6765-6816, 2017. ,
Random search and reproducibility for neural architecture search, Conference on Uncertainty in Artificial Intelligence UAI'2019, p.129, 2019. ,
Pareto multi-task learning, Advances in Neural Information Processing Systems NeurIPS'2019, pp.12037-12047, 2019. ,
,
Auto-deeplab: hierarchical neural architecture search for semantic image segmentation, IEEE Conf. on Computer Vision and Pattern Recognition, pp.82-92, 2019. ,
Auto-deeplab: Hierarchical neural architecture search for semantic image segmentation, IEEE Conf. on Computer Vision and Pattern Recognition CVPR'2019, pp.82-92, 2019. ,
Pruning deep neural networks by optimal brain damage, INTERSPEECH 15th Conf. Int. Speech Communication, pp.1092-1095 ,
, Hierarchical representations for efficient architecture search, 2017.
, Darts: Differentiable architecture search, 2018.
Structure learning for deep neural networks based on multiobjective optimization, IEEE Trans. Neural Networks Learn. Syst, vol.29, issue.6, pp.2450-2463, 2018. ,
End-to-end multi-task learning with attention, IEEE Conf. on Computer Vision and Pattern Recognition CVPR'2019, pp.1871-1880, 2019. ,
Multi-objective autotuning of mobilenets across the full software/hardware stack, Int. Conf. on Reproducible Quality-Efficient Systems Tournament on Co-designing Paretoefficient Deep Learning, pp.6-16, 2018. ,
Deepmaker: A multi-objective optimization framework for deep neural networks in embedded systems, Microprocessors and Microsystems, p.102989, 2020. ,
Memetic evolution of deep neural networks, Genetic and Evolutionary Computation Conference GECCO, pp.505-512, 2018. ,
Hyperparameter selection in deep neural networks using parallel particle swarm optimization, Genetic and Evolutionary Computation Conference Companion, pp.1864-1871, 2017. ,
CMA-ES for hyperparameter optimization of deep neural networks, 2016. ,
NSGA-NET: A multi-objective genetic algorithm for neural architecture search, 2018. ,
A review of automatic selection methods for machine learning algorithms and hyper-parameter values, Network modeling Analysis in Health Informatics and Bioinformatics, vol.5, issue.1, p.18, 2016. ,
Neural architecture optimization, Advances in neural information processing systems, pp.7816-7827, 2018. ,
Deep neural architecture search with deep graph bayesian optimization, Int. Conf. on Web Intelligence WI'2019, pp.500-507, 2019. ,
Shake them all! -rethinking selection and replacement in MOEA/D, Int. Conf. on Parallel Problem Solving from Nature PPSN XIII, pp.641-651, 2014. ,
URL : https://hal.archives-ouvertes.fr/hal-00987800
Deep learning evolutionary optimization for regression of rotorcraft vibrational spectra, IEEE/ACM Machine Learning in HPC Environments, pp.57-66, 2018. ,
A genetic programming approach to designing convolutional neural network architectures, In IJCAI, 2018. ,
Signal reconstruction using evolvable recurrent neural networks, International Conference on Intelligent Data Engineering and Automated Learning, pp.594-602, 2018. ,
Towards automatically-tuned neural networks, Workshop on Automatic Machine Learning, pp.58-65, 2016. ,
Nonlinear multiobjective optimization, 1999. ,
Evolving deep neural networks, 2017. ,
A survey of fpga-based accelerators for convolutional neural networks, Neural computing and applications, pp.1-31, 2018. ,
Pruning convolutional neural networks for resource efficient transfer learning, 2016. ,
, Deeparchitect: Automatically designing and training deep architectures, 2017.
, Large-scale deep learning on the yfcc100m dataset, 2015.
GPU asynchronous stochastic gradient descent to speed up neural network training, 2nd Int. Conf. on Learning Representations ICLR, 2014. ,
Constructive neural-network learning algorithms for pattern classification, IEEE Trans. Neural Networks Learn. Syst, vol.11, issue.2, pp.436-451, 2000. ,
Big/little deep neural network for ultra low power inference, International Conference on Hardware/Software Codesign and System Synthesis, pp.124-132, 2015. ,
,
How to deal with mixed-variable optimization problems: An overview of algorithms and formulations, World Congress of Structural and Multidisciplinary Optimisation, pp.64-82, 2017. ,
URL : https://hal.archives-ouvertes.fr/hal-01690446
Bayesian optimization of variable-size design space problems, Optimization & Engineering Journal, 2020. ,
Efficient neural architecture search via parameter sharing, Int. Conf. on Machine Learning ICML, vol.80, pp.4092-4101 ,
Paleo: A performance model for deep neural networks, 5th Int. Conf. on Learning Representations ICLR, 2017. ,
, From nodes to networks: Evolving recurrent neural networks, 2018.
Hybrid stochastic GA-Bayesian search for deep convolutional neural network model selection, Journal of Universal Computer Science, vol.25, issue.6, pp.647-666, 2019. ,
Aging evolution for image classifier architecture search, AAAI Conf. on Artificial Intelligence, 2019. ,
Regularized evolution for image classifier architecture search, AAAI conference on artificial intelligence, vol.33, pp.4780-4789, 2019. ,
Large-scale evolution of image classifiers, Int. Conf. on Machine Learning, pp.2902-2911, 2017. ,
Fitnets: hints for thin deep nets, Int. Conf. on Learning Representations ICLR'2015, 2015. ,
Delight: Adding energy dimension to deep neural networks, Int. Symp. on Low Power Electronics and Design ISLPED, pp.112-117, 2016. ,
An overview of multi-task learning in, deep neural networks, 2017. ,
Convolutional neural fabrics, Advances in Neural Information Processing Systems, pp.4053-4061, 2016. ,
URL : https://hal.archives-ouvertes.fr/hal-01359150
Evaluating the search phase of neural architecture search, 2019. ,
Evaluating the search phase of neural architecture search, 2019. ,
Multi-task learning as multi-objective optimization, Advances in Neural Information Processing Systems, pp.527-538, 2018. ,
Horovod: fast and easy distributed deep learning in tensorflow, 2018. ,
Taking the human out of the loop: A review of bayesian optimization, Proceedings of the IEEE, vol.104, issue.1, pp.148-175, 2015. ,
Differentiable neural network architecture search, 2018. ,
Structure discovery of deep neural network based on evolutionary algorithms, IEEE Int. Conf. on Acoustics, Speech and Signal Processing (ICASSP), pp.4979-4983, 2015. ,
Very deep convolutional networks for large-scale image recognition, Int. Conf. on Learning Representations ICLR'2015, 2015. ,
Evolutionary multi-objective generation of recurrent neural network ensembles for time series prediction, Neurocomputing, vol.143, pp.302-311, 2014. ,
Neural networks designing neural networks: multi-objective hyper-parameter optimization, Int. Conf. on Computer-Aided Design, ICCAD'2016, p.104, 2016. ,
Practical bayesian optimization of machine learning algorithms, Advances in Neural Information Processing Systems, pp.2951-2959, 2012. ,
, Scalable bayesian optimization using deep neural networks. In Int. Conf. on Machine Learning, pp.2171-2180, 2015.
Bayesian optimization with robust bayesian neural networks, Advances in neural information processing systems, pp.4134-4142, 2016. ,
Landscapes and their correlation functions, Journal of Mathematical chemistry, vol.20, issue.1, pp.1-45, 1996. ,
Designing neural networks through neuroevolution, Nature Machine Intelligence, vol.1, issue.1, pp.24-35, 2019. ,
Evolving neural networks through augmenting topologies. Evolutionary computation, vol.10, pp.99-127, 2002. ,
Convolutional neural network architecture design by the tree growth algorithm framework, Int. Joint Conf. on Neural Networks IJCNN'2019, Hungary, vol.00, p.35, 2019. ,
Exploiting the potential of standard convolutional autoencoders for image restoration by evolutionary search, Int. Conf. on Machine Learning ICML, pp.4778-4787, 2018. ,
Sparsifying neural network connections for face recognition, Conf on Computer Vision and Pattern Recognition CVPR'2016, pp.4856-4864, 2016. ,
An experimental study on hyper-parameter optimization for stacked autoencoders, IEEE Congress on Evolutionary Computation (CEC), pp.1-8, 2018. ,
A particle swarm optimization-based flexible convolutional autoencoder for image classification, IEEE Trans. on Neural Networks and Learning Systems, vol.30, issue.8, pp.2295-2309, 2018. ,
, Raiders of the lost architecture: Kernels for bayesian optimization in conditional parameter spaces, 2014.
Going deeper with convolutions, Conf. on Computer Vision and Pattern Recognition, pp.1-9, 2015. ,
Rethinking the inception architecture for computer vision, Conf. on computer vision and pattern recognition, pp.2818-2826, 2016. ,
Metaheuristics: from design to implementation, 2009. ,
URL : https://hal.archives-ouvertes.fr/hal-00750681
A unified view of parallel multi-objective evolutionary algorithms, Journal of Parallel Distributed Computing, vol.133, pp.349-358, 2019. ,
URL : https://hal.archives-ouvertes.fr/hal-02304734
Mnasnet: Platform-aware neural architecture search for mobile, pp.2820-2828, 2019. ,
Auto-weka: Combined selection and hyperparameter optimization of classification algorithms, Int. Conf. on Knowledge Discovery and Data Mining, pp.847-855, 2013. ,
Evolving artificial neural networks using Cartesian genetic programming, 2015. ,
Learning time/memory-efficient deep architectures with budgeted supernetworks, Conf. on Computer Vision and Pattern Recognition CVPR, pp.3492-3500, 2018. ,
Evolving deep convolutional neural networks by variable-length particle swarm optimization for image classification, Congress on Evolutionary Computation (CEC), pp.1-8, 2018. ,
A hybrid differential evolution approach to designing deep convolutional neural networks for image classification, Australasian Joint Conf. on Artificial Intelligence, pp.237-250, 2018. ,
Evolving deep neural networks by multi-objective particle swarm optimization for image classification, Genetic and Evolutionary Computation Conference, pp.490-498, 2019. ,
Dlau: A scalable deep learning accelerator unit on fpga, IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, vol.36, issue.3, pp.513-517, 2016. ,
Evolutionary generative adversarial networks, IEEE Transactions on Evolutionary Computation, vol.23, issue.6, pp.921-934, 2019. ,
Alphax: exploring neural architectures with deep neural networks and monte carlo tree search, 2019. ,
Network morphism, Int. Conf. on Machine Learning, pp.564-572, 2016. ,
A survey of transfer learning, Journal of Big data, vol.3, issue.1, p.9, 2016. ,
Nas-unet: Neural architecture search for medical image segmentation, IEEE Access, vol.7, pp.44247-44257, 2019. ,
, Bananas: Bayesian optimization with neural architectures for neural architecture search, 2019.
A survey on neural architecture search, 2019. ,
Genetic CNN, IEEE Int. Conf. on Computer Vision, pp.1379-1388, 2017. ,
SNAS: stochastic neural architecture search, Int. Conf. on Learning Representations, ICLR'2019, 2019. ,
Multi-gpu training of convnets, Int. Conf. on Learning Representations ICLR, 2014. ,
, Nas-bench-101: Towards reproducible neural architecture search, 2019.
Optimizing deep learning hyper-parameters through an evolutionary algorithm, Workshop on Machine Learning in HPC Environments, pp.41-45, 2015. ,
Towards automated deep learning: efficient joint neural architecture and hyperparameter search, 2018. ,
Moea/d: A multiobjective evolutionary algorithm based on decomposition, IEEE Transactions on Evolutionary Computation, vol.11, issue.6, pp.712-731, 2007. ,
,
You only search once: single shot neural architecture search via direct sparse optimization, 2018. ,
A power-efficient accelerator based on FPGAs for LSTM network, IEEE Int. Conf. on Cluster Computing (CLUSTER), pp.629-630, 2017. ,
, DNA computing inspired deep networks design. Neurocomputing, vol.382, pp.140-147, 2020.
Practical network blocks design with q-learning, 2017. ,
Practical block-wise neural network architecture generation, IEEE Conf. on Computer Vision and Pattern Recognition, pp.2423-2432, 2018. ,
, Resource-efficient neural architect, 2018.
Structured binary neural networks for accurate image classification and semantic segmentation, IEEE Conf. on Computer Vision and Pattern Recognition, pp.413-422, 2019. ,
Neural architecture search with reinforcement learning, Int. Conf. on Learning Representations ICLR, 2017. ,
Learning transferable architectures for scalable image recognition, IEEE Conf. on Computer Vision and Pattern Recognition, pp.8697-8710, 2018. ,