Abstract
The paper introduces a novel modality to efficiently tune the convolutional layers of a deep neural network (CNN) and an approach to also rank the importance of the involved hyperparameters. Evolutionary algorithms (EA) offer a flexible solution to this twofold issue, while the expensive simulations of the deep learner with the generated configurations are resolved by surrogate modelling. Three models have been used and evaluated as surrogates: random forests (RF), support vector machines (SVM) and Kriging. Sample convolutional configurations are generated by Latin hypercube sampling and have attached computed accuracy outcomes from real CNN runs. For the hyperparameter estimation task, the fitness of an individual from the EA associated with a surrogate model is subsequently derived from the CNN accuracy estimation on those variable values. With respect to the ranking and variable selection task, RF includes implicit variable selection, the SVM can be straightforwardly supported by a second EA, and Kriging offers a ranking based on the corresponding θ values. The estimated accuracy of the found hyperparameter values is compared with the true validation accuracy, and they are next used for the prediction on the test cases. The ranking of the variables for each of the three surrogate models is compared, and their influence is also revealed by response surface methodology. The experimental testing of the proposed EA–surrogate approaches is conducted on a real-world scenario of histopathological image interpretation in colorectal cancer diagnosis.
Similar content being viewed by others
References
Albarqouni S, Baur C, Achilles F, Belagiannis V, Demirci S, Navab N (2016) Aggnet: deep learning from crowds for mitosis detection in breast cancer histology images. IEEE Trans Med Imaging 35(5):1313–1321. https://doi.org/10.1109/TMI.2016.2528120
Arunkumar R, Karthigaikumar P (2017) Multi-retinal disease classification by reduced deep learning features. Neural Comput Appl 28(2):329–334. https://doi.org/10.1007/s00521-015-2059-9
Atencia M, Joya G, Sandoval F (2004) Parametric identification of robotic systems with stable time-varying hopfield networks. Neural Comput Appl 13(4):270–280. https://doi.org/10.1007/s00521-004-0421-4
Bacciu D, Lisboa PJG, Martín JD, Stoean R, Vellido A (2018) Bioinformatics and medicine in the era of deep learning. CoRR arXiv:1802.09791
Bartz-Beielstein T, Zaefferer M (2017) Model-based methods for continuous and discrete global optimization. Appl Soft Comput 55:154–167. https://doi.org/10.1016/j.asoc.2017.01.039
Cireşan DC, Giusti A, Gambardella LM, Schmidhuber J (2013) Mitosis detection in breast cancer histology images with deep neural networks. Springer, Berlin, pp 411–418
Eiben AE, Smith JE (2003) Introduction to evolutionary computing. Springer, Berlin
Forrester AIJ, Sbester A, Keane AJ (2008) Engineering design via surrogate modelling: a practical guide. Wiley, New York
Friese M, Bartz-Beielstein T, Emmerich M (2016) Building ensembles of surrogates by optimal convex combination. In: Papa G, Mernik M (eds) Bioinspired optimization methods and their applications. Jožef Stefan Institute, Lubljana, pp 131–143
Gorunescu F, Belciug S (2016) Boosting backpropagation algorithm by stimulus-sampling: application in computer-aided medical diagnosis. J Biomed Inform 63:74–81. https://doi.org/10.1016/j.jbi.2016.08.004
Hackl C (2014) Calibration and parameterization methods for the libor market model. Springer, Berlin
Heaton JB, Polson NG, Witte JH (2017) Deep learning for finance: deep portfolios. Appl Stoch Models Bus Ind 33(1):3–12. https://doi.org/10.1002/asmb.2209
Jiang F, Grigorev A, Rho S, Tian Z, Fu Y, Jifara W, Adil K, Liu S (2017) Medical image semantic segmentation based on deep learning. Neural Comput Appl. https://doi.org/10.1007/s00521-017-3158-6
Jin Y (2011) Surrogate-assisted evolutionary computation: recent advances and future challenges. Swarm Evolut Comput 1(2):61–70
Field RV Jr, Constantine P, Boslough M (2013) Statistical surrogate models for prediction of high-consequence climate change. Int J Uncertain Quant 3(4):341–355
Kapás Z, Lefkovits L, Iclanzan D, Gyorfi Á, Iantovics B, Lefkovits S, Szilágyi SM, Szilágyi L (2017) Automatic brain tumor segmentation in multispectral MRI volumes using a random forest approach. PSIVT 10749:137–149
Loshchilov I, Hutter F (2016) CMA-ES for hyperparameter optimization of deep neural networks. CoRR arXiv:1604.07269
Malshe M, Narulkar R, Raff LM, Hagan M, Bukkapatnam S, Komanduri R (2008) Parametrization of analytic interatomic potential functions using neural networks. J Chem Phys 129(4):044,111. https://doi.org/10.1063/1.2957490
Martens D, Baesens B, Gestel TV (2009) Decompositional rule extraction from support vector machines by active learning. IEEE Trans Knowl Data Eng 21(2):178–191. https://doi.org/10.1109/TKDE.2008.131
McKay MD, Beckman RJ, Conover WJ (1979) A comparison of three methods for selecting values of input variables in the analysis of output from a computer code. Technometrics 21(2):239–245
Paja W, Pancerz K (2017) Feature selection methods applied to severe brain damages data. In: 2017 Federated conference on computer science and information systems (FedCSIS), pp 199–202. https://doi.org/10.15439/2017F382
Postavaru S, Stoean R, Stoean C, Joya G (2017) Adaptation of deep convolutional neural networks for cancer grading from histopathological images. In: Advances in computational intelligence: 14th international work-conference on artificial neural networks, IWANN 2017, Cadiz, Spain, 14–16 June 2017, Proceedings, Part II, Rojas, Ignacio and Joya, Gonzalo and Catala, Andreu (eds). Springer International Publishing, Cham, pp 38–49
Preuss M (2015) Multimodal optimization by means of evolutionary algorithms. Natural computing series. Springer, Berlin. https://doi.org/10.1007/978-3-319-07407-8
Sikora EBTST (2017) Hyper-parameter optimization for convolutional neural network committees based on evolutionary algorithms. In: International conference on image processing. IEEE SigPort. http://sigport.org/2022
Sirinukunwattana K, Raza SEA, Tsang YW, Snead DRJ, Cree IA, Rajpoot NM (2016) Locality sensitive deep learning for detection and classification of nuclei in routine colon cancer histology images. IEEE Trans Med Imaging 35(5):1196–1206. https://doi.org/10.1109/TMI.2016.2525803
Stoean C (2016) In search of the optimal set of indicators when classifying histopathological images. In: 2016 18th International symposium on symbolic and numeric algorithms for scientific computing (SYNASC), pp 449–455. https://doi.org/10.1109/SYNASC.2016.074
Stoean C, Preuss M, Stoean R (2013) EA-based parameter tuning of multimodal optimization performance by means of different surrogate models. In: Genetic and evolutionary computation conference, GECCO 2013. ACM, pp 1063–1070. https://doi.org/10.1145/2464576.2482684
Stoean C, Stoean R, Sandita A, Ciobanu D, Mesina C, Gruia CL (2016) SVM-based cancer grading from histopathological images using morphological and topological features of glands and nuclei. Springer, Berlin, pp 145–155. https://doi.org/10.1007/978-3-319-39345-2_13
Taylor S, Kim T, Yue Y, Mahler M, Krahe J, Rodriguez AG, Hodgins J, Matthews I (2017) A deep learning approach for generalized speech animation. ACM Trans Graph 36(4):93:1–93:11. https://doi.org/10.1145/3072959.3073699
Urda D, Montes-Torres J, Moreno F, Franco L, Jerez JM (2017) Deep learning to analyze RNA-Seq gene expression data. Springer International Publishing, Berlin, pp 50–59. https://doi.org/10.1007/978-3-319-59147-6_5
Volz V, Rudolph G, Naujoks B (2017) Investigating uncertainty propagation in surrogate-assisted evolutionary algorithms. In: Proceedings of the genetic and evolutionary computation conference, GECCO ’17. ACM, New York, NY, USA, pp 881–888. https://doi.org/10.1145/3071178.3071249
Yoon JG, Heo J, Kim M, Park YJ, Choi MH, Song J, Wyi K, Kim H, Duchenne O, Eom S, Tsoy Y (2018) Machine learning-based diagnosis for disseminated intravascular coagulation (DIC): development, external validation, and comparison to scoring systems. PLOS ONE 13(5):1–15. https://doi.org/10.1371/journal.pone.0195861
Young SR, Rose DC, Karnowski TP, Lim SH, Patton RM (2015) Optimizing deep learning hyper-parameters through an evolutionary algorithm. In: Proceedings of the workshop on machine learning in high-performance computing environments. ACM, pp 4:1–4:5. https://doi.org/10.1145/2834892.2834896
Zhang J, Chowdhury S, Messac A (2012) An adaptive hybrid surrogate model. Struct Multidiscip Optim 46(2):223–238. https://doi.org/10.1007/s00158-012-0764-x
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of Interest
The authors declare that they have no conflict of interest.
Rights and permissions
About this article
Cite this article
Stoean, R. Analysis on the potential of an EA–surrogate modelling tandem for deep learning parametrization: an example for cancer classification from medical images. Neural Comput & Applic 32, 313–322 (2020). https://doi.org/10.1007/s00521-018-3709-5
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-018-3709-5