Abstract
Each time an artificial neural network learns an unseen dataset, it loses its ability to recognize the feature that it had learned before. This phenomenon is called the catastrophic forgetting problem (CFP). In image classification, the representative feature of each class that has significantly contributed to determining the class into which a given an image is categorized and thus directly influences performance. CFP can thus be damaging. The proposed algorithm, called Predictive EWC or PEWC, learns only sampled data from a new task consisting of the most challenging images for the network to classify. The criterion for extracting a sample is the absolute value of the difference between the network’s predicted value and the annotated value of the given image. This reduces the size of the task to be learned and mitigates the likelihood of CFP. An experiment showed that the average accuracy of a given task is 5% higher when the proposed algorithm is used in comparison with a prevalent algorithm, EWC, while consuming fewer resources.
Similar content being viewed by others
References
Abraham WC, Robins A (2005) Memory retention-synaptic stability versus plasticity dilemma. Trends Neurosci 28(2):73–78
Becker S, Zhang Y, Lee AA (2018) Geometry of energy landscapes and the optimizability of deep neural networks. arXiv:1808.00408
Chen LC, Papandreou G, Kokkinos L, Murphy K, Yuille AL (2018) DeepLab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs. IEEE Trans Pattern Anal Mach Intell 40(4):834–848
Coop R, Mishtal A, Arel I (2013) Ensemble learning in fixed expansion layer networks for mitigating catastrophic forgetting. IEEE Trans Neural Netw Learn Syst 24(10):1623–1634
Gepperth A, Karaoguz C (2016) A bio-inspired incremental learning architecture for applied perceptual problems. Cogn Comput 8(5):924–934
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
Kafle K, Kanan C (2017) Visual question answering: datasets, algorithms, and future challenges. Comput Vis Image Underst 163:3–20
Kemker R, McClure M, Abitino A, Hayes TL, Kanan C (2018) Measuring catastrophic forgetting in neural networks. In: Thirty-second AAAI conference on artificial intelligence
Khilari P, Bhope VP (2015) A review on speech to text conversion methods. Int J Adv Res Comput Eng Technol 4:3067–3072
Kirkpatrick J, Pascanu R, Rabinowitz N, Veness J, Desjardins G, Rusu AA, Milan K, Quan J, Ramalho T, Grabska-Barwinska A, Hassabis D, Clopath C, Kumaran D, Hadsell R (2017) Overcoming catastrophic forgetting in neural networks. Proc Natl Acad Sci. https://doi.org/10.1073/pnas.1611835114
Kyung-Mo K, Eui-Young C (2017) Image recognition performance enhancements using image normalization. Hum Centric Comput Inf Sci 7(1):33
LeCun YA, Cortes C, Burges CJ (1998) The MNIST database of handwritten digits. http://yann.lecun.com/exdb/mnist/. Accessed 11 Oct 2018
LeCun YA et al (2012) Efficient backprop. In: Neural networks: tricks of the trade. Lecture notes in computer science, vol 7700, pp 9–48
McCloskey M, Cohen NJ (1989) Catastrophic interference in connectionist networks: the sequential learning problem. Psychology of learning and motivation, vol 24. Academic Press, London, pp 109–165
Mnih V, Kavukcuoglu K, Silver D, Graves A, Antonoglou I, Wierstra D, Riedmiller M (2013) Playing atari with deep reinforcement learning. CoRR abs/1312.5602
Ning Y, Zeng Y, Feng G, Tianrui L, Xinmin T, Yi P (2017) Deep learning in genomic and medical image data analysis: challenges and approaches. J Inf Process Syst 13(2):204–214
Oquab M, Bottou L, Laptev I, Sivic J (2014) Learning and transferring mid-level image representations using convolutional neural networks. In: The IEEE conference on computer vision and pattern recognition, pp 1717–1724
Ren B, Wang H, Li J, Gao H (2017) Life-long learning based on dynamic combination model. Appl Soft Comput 56:398–404
Robins A (1995) Catastrophic forgetting, rehearsal and pseudo-rehearsal. Connect Sci 7(2):123–146
Sang-Geol L, Yunsick S, Yeon-Gyu K, Eui-Young C (2018) Variatiaons of AlexNet and GoogLeNet to improve korean character recognition performance. J Inf Process Syst 14(1):205–217
Schroff F, Kalenichenko D, Philbin J (2015) Facenet: a unified embedding for face recognition and clustering. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 815–823
Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556
Song Z, Sheng X (2018) 3D face recognition: a survey. Hum Centric Comput Inf Sci. https://doi.org/10.1186/s13673-018-0157-2
Wang X, Peng Y, Lu L, Lu Z, Bagheri M, Summers RM (2017) ChestX-ray8: Hospital-scale chest x-ray database and benchmarks on weakly-supervised classification and localization of common thorax diseases. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2097–2106
Acknowledgements
This work was supported by INHA University Grant.
Author information
Authors and Affiliations
Corresponding author
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
Hong, D., Li, Y. & Shin, BS. Predictive EWC: mitigating catastrophic forgetting of neural network through pre-prediction of learning data. J Ambient Intell Human Comput (2019). https://doi.org/10.1007/s12652-019-01346-7
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s12652-019-01346-7