Abstract
Based on the theory of local receptive field based extreme learning machine (ELM-LRF) and ELM auto encoder (ELM-AE), a new network structure is proposed to take advantage of global attributes of image and output feature of each layer in the structure. This proposed network structure is called extreme learning machine with autoencoding receptive fields (ELM-ARF), which has two parts including convolution feature extraction and feature coding. In the convolution feature extraction part, local features are extracted using orthogonalized local receptive fields. The ELM-AE theory and local receptive fields are used to encode the global receptive fields, which is used to extract global features. The pooled global features and local features are combined and input into the next layer. In the feature coding part, the shallow layer feature can be input to any deep layer through the ELM-ARF connection structure. A series of encodings are performed on the combined features in each layer to achieve a nonlinear mapping relationship from input information to target categories. In order to verify the validity of the structure, ELM-ARF is tested on four classic databases: USPS, MNIST, NORB and CIFAR10. The experimental results show that ELM-ARF effectively improves image classification accuracy by encoding the combined features that contain global attributes.















Similar content being viewed by others
Explore related subjects
Discover the latest articles and news from researchers in related subjects, suggested using machine learning.References
Huang GB, Chen L (2007) Convex incremental extreme learning machine. Neurocomputing 70(16–18):3056–3062
Huang GB, Chen L (2008) Enhanced random search based incremental extreme learning machine. Neurocomputing 71(16–18):3460–3468
Huang GB, Zhu QY, Siew CK (2004) Extreme learning machine: a new learning scheme of feedforward neural networks. Neural Netw 2:985–990
Huang GB, Zhu QY, Siew CK (2006) Extreme learning machine: theory and applications. Neurocomputing 70(1–3):489–501
Huang GB, Zhou H, Ding X, Zhang R (2012) Extreme learning machine for regression and multiclass classification. IEEE Trans Syst Man Cybern Part B Cybern 42(2):513–529
Koniusz P, Yan F, Gosselin PH, Mikolajczyk K (2017) Higher-order occurrence pooling for bags-of-words: visual concept detection. IEEE Trans Pattern Anal Mach Intell 39(2):313–326
Lazebnik S, Schmid C, Ponce J (2006) Beyond bags of features: spatial pyramid matching for recognizing natural scene categories. IEEE Comput Soc Conf Comput Vis Pattern Recognit 2:2169–2178
Han HG, Wang LD, Qiao JF (2014) Hierarchical extreme learning machine for feedforward neural network. Neurocomputing 128:128–135
Li G, Niu P, Duan X, Zhang X (2014) Fast learning network: a novel artificial neural network with a fast learning speed. Neural Comput Appl 24(7–8):1683–1695
Qu BY, Lang B, Liang JJ, Qin AK, Crisalle OD (2016) Two-hidden-layer extreme learning machine for regression and classification. Neurocomputing 175:826–834
Huang GB, Bai Z, Kasun LLC, Vong CM (2015) Local receptive fields based extreme learning machine. IEEE Comput Intell Mag 10(2):18–29
Huang G, Liu Z, Van Der Maaten L, Weinberger KQ (2017) Densely connected convolutional networks. Proc IEEE Conf Comput Vis Pattern Recognit 2:4700–4708
Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. In: Advances in neural information processing systems, pp 1097–1105
Zhang H, Cao X, Ho JK, Chow TW (2017) Object-level video advertising: an optimization framework. IEEE Trans Industr Inf 13(2):520–531
Zhang H, Ji Y, Huang W, Liu L (2018) Sitcom-star-based clothing retrieval for video advertising: a deep learning framework. In: Neural computing and applications, pp 1–20
Rumelhart DE, Hinton GE, Williams RJ (1986) Learning representations by back-propagating errors. Cogn Model 5(3):1
Ding S, Guo L, Hou Y (2017) Extreme learning machine with kernel model based on deep learning. Neural Comput Appl 28(8):1975–1984
Pang S, Yang X (2016) Deep convolutional extreme learning machine and its application in handwritten digit classification. In: Computational intelligence and neuroscience, pp 1–10
Liu H, Li F, Xu X, Sun F (2018) Multi-modal local receptive field extreme learning machine for object recognition. Neurocomputing 277:4–11
Huang J, Yu ZL, Cai Z, Gu Z, Cai Z, Gao W, Yu S, Du Q (2017) Extreme learning machine with multi-scale local receptive fields for texture classification. Multidimens Syst Signal Process 28(3):995–1011
He B, Song Y, Zhu Y, Sha Q, Shen Y, Yan T, Nian R, Lendasse A (2018) Local receptive fields based extreme learning machine with hybrid filter kernels for image classification. In: Multidimensional systems and signal processing, pp 1–21
Kasun LLC, Zhou H, Huang GB, Vong CM (2013) Representational learning with extreme learning machine for big data. IEEE Intell Syst 28(6):31–34
He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770–778
Lu J, Lu Y, Cong G (2011) Reverse spatial and textual k nearest neighbor search. In: Proceedings of the 2011 ACM SIGMOD international conference on management of data. ACM, pp 349–360
LeCun Y, Bottou L, Bengio Y, Haffner P (1998) Gradient-based learning applied to document recognition. Proc IEEE 86(11):2278–2324
LeCun Y, Huang FJ, Bottou L (2004) Learning methods for generic object recognition with invariance to pose and lighting. In: Proceedings of the computer vision and pattern recognition, pp 97–104
Krizhevsky A, Hinton G (2009) Learning multiple layers of features from tiny images. Technical report, University of Toronto, vol 1, p 7
Chen J, Wu Z, Zhang J, Li F, Li W, Wu Z (2018) Cross-covariance regularized autoencoders for nonredundant sparse feature representation. Neurocomputing 316:49–58
Wang Y, Xie Z, Xu K, Dou Y, Lei Y (2016) An efficient and effective convolutional auto-encoder extreme learning machine network for 3d feature learning. Neurocomputing 174:988–998
Vong CM, Chen C, Wong PK (2018) Empirical kernel map-based multilayer extreme learning machines for representation learning. Neurocomputing 310:265–276
Acknowledgments
This work is supported by National Natural Science Foundation of China (No. 51641609).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Wu, C., Li, Y., Zhao, Z. et al. Extreme learning machine with autoencoding receptive fields for image classification. Neural Comput & Applic 32, 8157–8173 (2020). https://doi.org/10.1007/s00521-019-04303-9
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-019-04303-9