Abstract
A deep learning network is super-efficient for image processing. The artificial brain of the deep learning system is highly capable of solving the categorization of problems. However, deep learning has several restrictions on the intelligence of the human brain. The human brain can update and improve knowledge by analyzing the features of images. In the artificial brain, the arrangements of the pixels are used for image understanding. This pixel-based continuous learning tendency of the artificial brain of deep learning leading to reducing the knowledge of previously achieved relevant information of the system is called the catastrophic forgetting problem of deep learning. Recently, many researchers reported that the catastrophic forgetting problem affects the result of deep learning. So, in this study, we are providing an excellent solution for the catastrophic forgetting problem of deep learning by restricting the direct analysis of input images with image morphological features. This image morphological feature-based deep learning system helps the artificial brain to concentrate on image features. This image morphological features system-based study achieved a stable learning graph with 80% average learning accuracy.
Similar content being viewed by others
References
Albesano D, Gemello R, Laface P, Mana F, Scanzio S (2006) Adaptation of Artificial Neural Networks Avoiding Catastrophic Forgetting. IEEE International Joint Conference on Neural Network Proceedings, pp. 1554–1561. https://doi.org/10.1109/IJCNN.2006.246618.
Aly H, Youssef SM (2023) Bio-signal based motion control system using deep learning models: a deep learning approach for motion classification using EEG and EMG signal fusion. J Ambient Intell Human Comput 14:991–1002. https://doi.org/10.1007/s12652-021-03351-1
Arora M, Mangipudi P, Dutta MK (2021) Deep learning neural networks for acrylamide identification in potato chips using transfer learning approach. J Ambient Intell Human Comput 12:10601–10614. https://doi.org/10.1007/s12652-020-02867-2
Bouwmans T, Javed S, Sultana M, Jung SK (2019) Deep neural network concepts for background subtraction: a systematic review and comparative evaluation. Neural Netw 117:8–66. https://doi.org/10.1016/j.neunet.2019.04.024
Chen Z, Bing Liu (2018) Lifelong Machine Learning. Morgan & Claypool Publishers 2.
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. https://doi.org/10.1109/TNNLS.2013.2264952
Coop R and Arel I (2013) Mitigation of catastrophic forgetting in recurrent neural networks using a Fixed Expansion Layer, International Joint Conference on Neural Networks Proceedings, pp.1–7, https://doi.org/10.1109/IJCNN.2013.6707047.
Darem AA, Ghaleb FA, Al-Hashmi AA, Abawajy JH, Alanazi SM, Al-Rezami AY (2021) An adaptive behavioral-based incremental batch learning malware variants detection model using concept drift detection and sequential deep learning. IEEE Access 9:97180–97196. https://doi.org/10.1109/ACCESS.2021.3093366
French RM (1999) Catastrophic forgetting in connectionist networks. Trends Cogn Sci 3(4):128–135. https://doi.org/10.1016/S1364-6613(99)01294-2
Gronde JJVD, Roerdink JBTM (2014) Group-invariant colour morphology based on frames. IEEE Trans Image Process 23(3):1276–1288. https://doi.org/10.1109/TIP.2014.2300816
Hedberg H, Dokladal P, Owall V (2009) Binary morphology with spatially variant structuring elements: algorithm and architecture. IEEE Trans Image Process 18(3):562–572. https://doi.org/10.1109/TIP.2008.2010108
Hong D, Li Y, Shin BS (2019) Predictive EWC: mitigating catastrophic forgetting of neural network through pre-prediction of learning data. J Ambient Intell Human Comput. https://doi.org/10.1007/s12652-019-01346-7
Hu R, Jia W, Ling H, Huang D (2012) Multiscale distance matrix for fast plant leaf recognition. IEEE Trans Image Process 21(11):4667–4672. https://doi.org/10.1109/TIP.2012.2207391
Huo J, Zyl TLv (2020) Comparative Analysis of Catastrophic Forgetting in Metric Learning. 7th International Conference on Soft Computing and Machine Intelligence, pp.68–72. https://doi.org/10.1109/ISCMI51676.2020.9311580.
Hurtado J, Lobel H, Soto A, (2021) Overcoming catastrophic forgetting using sparse coding and meta learning. IEEE Access 9: 88279–88290. https://doi.org/10.1109/ACCESS.2021.3090672.
Ikenaga T, Ogura T (2000) Real-time morphology processing using highly parallel 2-D cellular automata CAM/sup 2/. IEEE Trans Image Process 9(12):2018–2026. https://doi.org/10.1109/83.887970
Jayachitra S, Prasanth A (2021) Multi-feature analysis for automated brain stroke classification using weighted gaussian naive Baye’s classifier. J Circuits, Syst Comput 30(10):2150178. https://doi.org/10.1142/S0218126621501784
Jayachitra S, Prasanth A, Haleem SLA, Amin SM, Shaik K (2022) An efficient clinical support system for heart disease prediction using TANFIS classifier. Comput Intell 38(2):610–640. https://doi.org/10.1111/coin.12487
Jibi GT, Dubey AK, Thomas MT (2017) Whether color, shape and texture of leaves are the key features for image processing based plant recognition? An analysis!. Recent Developments in Control, Automation & Power Engineering Proceedings 404–409. doi: https://doi.org/10.1109/RDCAPE.2017.8358305
Jibi GT, Dubey AK, Thomas MT (2022a) Deep learning based aquatic and semi aquatic plants morphological features extraction and classification. Int J Performability Eng 18(10):702–709. https://doi.org/10.23940/ijpe.22.10.p3.702-709
Jibi GT, Dubey AK, Thomas MT (2022b) Importance of image morphological features in continues learning. In: International mobile and embedded technology conference proceedings, pp 372–376. https://doi.org/10.1109/MECON53876.2022.9752445
Jibi GT, Dubey AK, Thomas MT (2023a) Deep - Morpho Algorithm (DMA) for medicinal leaves features extraction. Multimed Tools Appl. https://doi.org/10.1007/s11042-023-14567-y
Jibi GT, Dubey AK, Thomas MT (2023b) A novel edge detection method for medicinal plant’s leaf features extraction. Int J Syst Assur Eng Manag 14:448–458. https://doi.org/10.1007/s13198-022-01814-y
Jung H, Ju J, Jung M, Kim J (2016) Less-forgetting Learning in Deep Neural Networks. ArXiv vol. abs/1607.00122. https://doi.org/10.48550/arXiv.1607.00122
Kaur P, Shilpi H, Vinay G, Mukund PS, Santar PS (2022) A novel transfer deep learning method for detection and classification of plant leaf disease. J Ambient Intell Human Comput. https://doi.org/10.1007/s12652-022-04331-9
Khatib AE, Karray F (2019) Preempting Catastrophic Forgetting in Continual Learning Models by Anticipatory Regularization. International Joint Conference on Neural Networks, pp.1–7. doi: https://doi.org/10.1109/IJCNN.2019.8852426.
Kim G, Hwang CS, Jeong DS (2019) Stochastic Learning with Back Propagation. IEEE International Symposium on Circuits and Systems, pp. 1–5. doi: https://doi.org/10.1109/ISCAS.2019.8702253.
Kirkpatrick J, Pascanu R, Rabinowitz N, Veness J, Desjardins G, Rusu AA, Milan K, Quan J, Ramalho T, Grabska-Barwinska A, Has-sabis D, Clopath C, Kumaran D, Hadsell R (2017) Overcoming catastrophic forgetting in neural networks. Proc Natl Acad Sci 114(13):3521–3526. https:// doi. org/ 10. 1073/ pnas. 16118 35114
Kujani T, Kumar VD (2021) Head movements for behavior recognition from real time video based on deep learning ConvNet transfer learning. J Ambient Intell Human Comput. https://doi.org/10.1007/s12652-021-03558-2
Lee CY, Shon JG, Park JS (2022) An edge detection–based eGAN model for connectivity in ambient intelligence environments. J Ambient Intell Human Comput 13:4591–4600. https://doi.org/10.1007/s12652-021-03261-2
Lee K, Lee K, Shin J, Lee H (2019) Overcoming Catastrophic Forgetting With Unlabeled Data in the Wild. IEEE/CVF International Conference on Computer Vision, pp.312–321. doi: https://doi.org/10.1109/ICCV.2019.00040.
Li Z, Hoiem D (2018) Learning without forgetting. IEEE Trans Pattern Analy Machine Intelligence 40(12):2935–2947. https://doi.org/10.1109/TPAMI.2017.2773081
Li X, Wang W (2023) GopGAN: gradients orthogonal projection generative adversarial network with continual learning”. IEEE Trans Neural Netw Learn Syst 34(1):215–227. https://doi.org/10.1109/TNNLS.2021.3093319
Li H, Barnaghi P, Enshaeifar S, Ganz F (2021) Continual Learning Using Bayesian Neural Networks. IEEE Trans Neural Netw Learn Syst 32(9):4243–4252. https://doi.org/10.1109/TNNLS.2020.3017292
Liu L, Kuang Z, Chen Y, Xue JH, Yang W, Zhang W (2021) IncDet: In Defense of elastic weight consolidation for incremental object detection. IEEE Trans Neural Netw Learn Syst 32 (6): 2306–2319. doi: https://doi.org/10.1109/TNNLS.2020.3002583.
Manneschi L, Lin AC, Vasilaki E (2023) SpaRCe: improved learning of reservoir computing systems through sparse representations. IEEE Trans Neural Netw Learn Syst 34(2):824–838. https://doi.org/10.1109/TNNLS.2021.3102378
Maragos P (1996) Differential morphology and image processing. IEEE Trans Image Process 5(6):922–937. https://doi.org/10.1109/83.503909
Masarczyk W, Tautkute I (2020) Reducing catastrophic forgetting with learning on synthetic data. IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp. 1019–1024. doi: https://doi.org/10.1109/CVPRW50498.2020.00134.
MvdV G, Siegelmann HT, Tolias AS (2020) Brain-inspired replay for continual learning with artificial neural networks. Nat Commun 11:4069. https://doi.org/10.1038/s41467-020-17866-2
Nakano S, Hattori M (2017) Reduction of catastrophic forgetting in multilayer neural networks trained by contrastive Hebbian Learning with pseudorehearsal. IEEE 10th International Workshop on Computational Intelligence and Applications, pp. 91–95. doi: https://doi.org/10.1109/IWCIA.2017.8203567.
Parisi GI, Kemker R, Part JL, Kanan C, Wermter S (2019) Continual lifelong learning with neural networks: a review. Neural Netw 113:54–71. https://doi.org/10.1016/j.neunet.2019.01.012
Park GM, Yoo SM, Kim JH (2021) Convolutional neural network with developmental memory for continual learning. IEEE Trans Neural Netw Learn Syst 32(6):2691–2705. https://doi.org/10.1109/TNNLS.2020.3007548
Pathak RK, Yadav V (2020) Improvised Progressive Neural Network (iPNN) for Handling Catastrophic Forgetting. International Conference on Electronics and Sustainable Communication Systems, pp.143–148. doi: https://doi.org/10.1109/ICESC48915.2020.9156028.
Peng J, Bo T, Hao J, Zhuo L, Yinjie L, Tao L, Haifeng L (2022) Overcoming long-term catastrophic forgetting through adversarial neural pruning and synaptic consolidation. IEEE Trans Neural Netw Learn Syst 33(9):4243–4256. https://doi.org/10.1109/TNNLS.2021.3056201
Robins A (1993) Catastrophic forgetting in neural networks: the role of rehearsal mechanisms. Proceedings of the First New Zealand International Two-Stream Conference on Artificial Neural Networks and Expert Systems 65–68. doi: https://doi.org/10.1109/ANNES.1993.323080.
Serrà J, Surís D, Miron M, Karatzoglou A (2018) Overcoming catastrophic forgetting with hard attention to the task. Proceedings of the 35th International Conference on Machine Learning, pp. arXiv:1801.01423 [cs.LG]. https://doi.org/10.48550/arXiv.1801.01423
Siddiqui ZA, Park U (2021) Progressive convolutional neural network for incremental learning. Electronics 10(16):1879. https://doi.org/10.3390/electronics10161879
Sirois S, Spratling M, Thomas M, Westermann G, Mareschal D, Johnson MH (2008) Précis of Neuroconstructivism: how the brain constructs cognition. Behavioral and Brain Sciences 31(3):321–331. https://doi.org/10.1017/S0140525X0800407X
Su X, Guo S, Tan T, Chen F (2020) Generative memory for lifelong learning. IEEE Trans Neural Netw Learn Syst 31(6):1884–1898. https://doi.org/10.1109/TNNLS.2019.2927369
Suryawanshi S, Goswami A, Patil P, Mishra V (2022) Adaptive windowing based recurrent neural network for drift adaption in non-stationary environment. J Ambient Intell Human Comput. https://doi.org/10.1007/s12652-022-04116-0
Wang L, Lei B, Li Q, Su H, Zhu J, Zhong Y (2022) Triple-Memory Networks: a brain-inspired method for continual learning. IEEE Trans Neural Netw Learn Syst 33(5):1925–1934. https://doi.org/10.1109/TNNLS.2021.3111019
Wen S, Rios A, Ge Y, Itti L (2022) Beneficial perturbation network for designing general adaptive artificial intelligence systems. IEEE Trans Neural Netw Learn Syst 33(8):3778–3791. https://doi.org/10.1109/TNNLS.2021.3054423
Wu SG, Bao FS, Xu EY, Wang Y, Chang Y, Xiang Q (2007) A leaf recognition algorithm for plant classification using probabilistic neural network. IEEE international symposium on signal processing and information Technology, pp. 11–16, doi: https://doi.org/10.1109/ISSPIT.2007.4458016.
Xia Y, Feng D, Zhao R (2006) Morphology-based multifractal estimation for texture segmentation. IEEE Trans Image Process 15(3):614–623. https://doi.org/10.1109/TIP.2005.863029
Xie X, Ge S, Xie M, Hu F, Jiang N (2020) An improved industrial sub-pixel edge detection algorithm based on coarse and precise location. J Ambient Intell Human Comput 11:2061–2070. https://doi.org/10.1007/s12652-019-01232-2
Zhai M, Chen L, Tung F, He J, Nawhal M, Mori G (2019) Lifelong GAN: Continual Learning for Conditional Image Generation. IEEE/CVF International Conference on Computer Vision, pp. 2759–2768. doi: https://doi.org/10.1109/ICCV.2019.00285.
Zhang B, Guo Y, Li Y, He Y, Wang H, Dai Q (2022) Memory recall: a simple neural network training framework against catastrophic forgetting. IEEE Trans Neural Netw Learn Syst 33(5):2010–2022. https://doi.org/10.1109/TNNLS.2021.3099700
Zhao H, Wang H, Fu Y, Wu F, Li X (2022) Memory efficient class-incremental learning for image classification. IEEE Trans Neural Netw Learn Syst 33(10):5966–5977. https://doi.org/10.1109/TNNLS.2021.3072041
Funding
Not Applicable.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
There is no conflict of interest.
Ethical approval
Not Applicable.
Consent to participate
I consent to participate.
Consent for publication
I consent for publication.
Data availability
Available on request.
Code availability
Custom code.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Thanikkal, J.G., Dubey, A.K. & Thomas, M.T. A deep-feature based estimation algorithm (DFEA) for catastrophic forgetting. J Ambient Intell Human Comput 14, 16771–16784 (2023). https://doi.org/10.1007/s12652-023-04686-7
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12652-023-04686-7