计算机科学 ›› 2022, Vol. 49 ›› Issue (3): 225-231.doi: 10.11896/jsjkx.201100111
刘洋, 李凡长
LIU Yang, LI Fan-zhang
摘要： 以神经网络为基础的深度学习在大量领域取得优异成果,但其难以处理相似或未经训练的任务。深度学习在对新任务的学习和适应过程中存在困难,且对训练样本规模要求很高,造成泛化性和扩展性不佳的问题。元学习是一种新的学习框架,旨在解决传统学习方法难以解决的快速学习和适应新任务的问题。针对图像分类的元学习问题,文中提出了一种基于贝叶斯理论的纤维丛元学习算法(Fiber Bundle Meta-learning Algorithm,FBBML)。首先通过卷积神经网络提取支持数据集的图片信息,以得到图片的表示。然后构建数据特征的流形结构和数据特征到标签的纤维丛。最后输入查询集选取当前新任务的流形截面,从而获得适合新任务的纤维,得到图片的正确标签。实验结果表明,基于所提算法实现的模型(FBBML)在公共数据集(mini-ImageNet)上相比标准四层卷积神经网络的模型取得了最佳的准确率性能。同时将纤维丛理论引入元学习,使得算法本身具备更高的可解释性。
中图分类号:
| [1]HOSPEDALES T,ANTONIOU A,MICAELLI P,et al.Meta-learning in neural networks:a survey[J].arXiv:2004.05439,2020. [2]SAHA S,GAN Z,CHENG L,et al.Hierarchical Deep Learning Neural Network (HiDeNN):An artificial intelligence (AI) framework for computational science and engineering[J].Computer Methods in Applied Mechanics and Engineering,2021,373:113452. [3]TORREY L,SHAVLIK J.Transfer learning[M]//Handbook of Research on Machine Learning Applications and Trends:Algorithms,Methods,and Techniques.IGI global,2010:242-264. [4]GLASS G V.Primary,secondary,and meta-analysis of research[J].Educational Researcher,1976,5(10):3-8. [5]MAUDSLEY D B.A theory of meta-learning and principles of facilitation:an organismic perspective[D].University of Toronto,1980. [6]CHAN P K,STOLFO S J.Scaling learning by meta-learning over disjoint and partially replicated data[C]//Ninth Florida AI Research Symposium.1996. [7]BENSUSAN H,GIRAUD-CARRIER C G,KENNEDY C J.A higher-order approach to meta-learning [C]//Inductive Logic Programming,International Conference.London,UK,2000. [8]VILALTA R,DRISSI Y.A perspective View and Survey of Meta-Learning[J].Artificial Intelligence Review,2002,18:77-95. [9]FINN C,ABBEEL P,LEVINE S.Model-agnostic meta-learning for fast adaptation of deep networks [C]//Proceedings of the 34th International Conference on Machine Learning-Volume 70.JMLR.org,2017. [10]SEUNG H S.The manifold ways of perception[J].Science,2000,290(5500):2268-2269. [11]SILVA V D,TENENBAUM J B.Global versus local methods in nonlinear dimensionality reduction[C]//Proceedings of the 15th International Conference on Neural Information Processing Systems (NIPS).Cambridge,MA,USA:MIT Press,2002:721-728. [12]KÜHNEL W.Differential geometry[M].American Mathematical Soc.,2015. [13]ZHANG P,BAI Y,WANG D,et al.Few-shot Classification of Aerial Scene Images via Meta-learning[J].Remote Sensing,2021,13(1):108. [14]ZHANG J,LI F Z.Research on fiber bundle model based on Manifold Learning[J].Journal of Nanjing University:Natural Science Edition,2008,44(5):477-485. [15]LU M,LI F.Survey on lie group machine learning[J].Big Data Mining and Analytics,2020,3(4):235-258. [16]LI F,ZHANG L,ZHANG Z.Lie group machine learning[M].Walter de Gruyter GmbH & Co KG,2018. [17]KINGMA D P,WELLING M.Auto-encoding variational bayes[J].arXiv:1312.6114,2013. [18]LECUN Y,BOSER B,DENKER J S,et al.Backpropagation applied to handwritten zip code recognition[J].Neural Computation,1989,1(4):541-551. [19]ZHANG Y,YANG Q.A survey on multi-task learning[J].ar-Xiv:1707.08114,2017. [20]LU J S.Application of Monte Carlo method in integral solution[J].Mathematical Learning and Research:Teaching and Research Edition,2017(5):39. [21]LAKE B M,SALAKHUTDINOV R,GROSS J,et al.One shot learning of simple visual concepts[C]//Proceedings of the Annual Meeting of the Cognitive Science Society.2011. [22]RAVI S,LAROCHELLE H.Optimization as a model for few-shot learning[C]//Proceedings of the International Conference on Learning Representations (ICLR).2017. [23]VINYALS O,BLUNDELL C,LILLICRAP T,et al.Matchingnetworks for one shot learning[C]//Advances in Neural Information Processing Systems.2016:3630-3638. [24]FINN C,XU K,LEVINE S.Probabilistic model-agnostic meta-learning[C]//Advances in Neural Information Processing Systems.2018:9516-9527. [25]SNELL J,SWERSKY K,ZEMEL R.Prototypical networks for few-shot learning[C]//Advances in Neural Information Processing Systems.2017:4080-4090. [26]TRIANTAFILLOU E,ZEMEL R,URTASUN R.Few-shotlearning through an information retrieval lens[C]//Advances in Neural Information Processing Systems.2017:2255-2265. [27]LI Z,ZHOU F,CHEN F,et al.Meta-sgd:Learning to learnquickly for few shot learning[J].arXiv:1707.09835,2017. [28]MISHRA N,ROHANINEJAD M,CHEN X,et al.A SimpleNeural Attentive Meta-Learner[C]//International Conference on Learning Representations.2018. [29]YOON J,KIM T,DIA O,et al.Bayesian model-agnostic meta-learning[C]//Conference and Workshop on Neural Information Processing Systems.2018. [30]GORDON J,BRONSKILL J,BAUER M,et al.Meta-learningprobabilistic inference for prediction[C]//International Confe-rence on Learning Representations.2019. [31]ZHANG Y J.Image Information Fusion[M]//Handbook ofImage Engineering.Springer,Singapore,2021:1493-1512. [32]NIELSEN F.On a Generalization of the Jensen-Shannon Divergence and the Jensen-Shannon Centroid[J].Entropy,2020,22(2):221. |
| [1] | 陈志强, 韩萌, 李慕航, 武红鑫, 张喜龙. 数据流概念漂移处理方法研究综述 Survey of Concept Drift Handling Methods in Data Streams 计算机科学, 2022, 49(9): 14-32. https://doi.org/10.11896/jsjkx.210700112 |
| [2] | 周旭, 钱胜胜, 李章明, 方全, 徐常胜. 基于对偶变分多模态注意力网络的不完备社会事件分类方法 Dual Variational Multi-modal Attention Network for Incomplete Social Event Classification 计算机科学, 2022, 49(9): 132-138. https://doi.org/10.11896/jsjkx.220600022 |
| [3] | 周乐员, 张剑华, 袁甜甜, 陈胜勇. 多层注意力机制融合的序列到序列中国连续手语识别和翻译 Sequence-to-Sequence Chinese Continuous Sign Language Recognition and Translation with Multi- layer Attention Mechanism Fusion 计算机科学, 2022, 49(9): 155-161. https://doi.org/10.11896/jsjkx.210800026 |
| [4] | 李宗民, 张玉鹏, 刘玉杰, 李华. 基于可变形图卷积的点云表征学习 Deformable Graph Convolutional Networks Based Point Cloud Representation Learning 计算机科学, 2022, 49(8): 273-278. https://doi.org/10.11896/jsjkx.210900023 |
| [5] | 郝志荣, 陈龙, 黄嘉成. 面向文本分类的类别区分式通用对抗攻击方法 Class Discriminative Universal Adversarial Attack for Text Classification 计算机科学, 2022, 49(8): 323-329. https://doi.org/10.11896/jsjkx.220200077 |
| [6] | 陈泳全, 姜瑛. 基于卷积神经网络的APP用户行为分析方法 Analysis Method of APP User Behavior Based on Convolutional Neural Network 计算机科学, 2022, 49(8): 78-85. https://doi.org/10.11896/jsjkx.210700121 |
| [7] | 朱承璋, 黄嘉儿, 肖亚龙, 王晗, 邹北骥. 基于注意力机制的医学影像深度哈希检索算法 Deep Hash Retrieval Algorithm for Medical Images Based on Attention Mechanism 计算机科学, 2022, 49(8): 113-119. https://doi.org/10.11896/jsjkx.210700153 |
| [8] | 檀莹莹, 王俊丽, 张超波. 基于图卷积神经网络的文本分类方法研究综述 Review of Text Classification Methods Based on Graph Convolutional Network 计算机科学, 2022, 49(8): 205-216. https://doi.org/10.11896/jsjkx.210800064 |
| [9] | 闫佳丹, 贾彩燕. 基于双图神经网络信息融合的文本分类方法 Text Classification Method Based on Information Fusion of Dual-graph Neural Network 计算机科学, 2022, 49(8): 230-236. https://doi.org/10.11896/jsjkx.210600042 |
| [10] | 武红鑫, 韩萌, 陈志强, 张喜龙, 李慕航. 监督和半监督学习下的多标签分类综述 Survey of Multi-label Classification Based on Supervised and Semi-supervised Learning 计算机科学, 2022, 49(8): 12-25. https://doi.org/10.11896/jsjkx.210700111 |
| [11] | 金方焱, 王秀利. 融合RACNN和BiLSTM的金融领域事件隐式因果关系抽取 Implicit Causality Extraction of Financial Events Integrating RACNN and BiLSTM 计算机科学, 2022, 49(7): 179-186. https://doi.org/10.11896/jsjkx.210500190 |
| [12] | 齐秀秀, 王佳昊, 李文雄, 周帆. 基于概率元学习的矩阵补全预测融合算法 Fusion Algorithm for Matrix Completion Prediction Based on Probabilistic Meta-learning 计算机科学, 2022, 49(7): 18-24. https://doi.org/10.11896/jsjkx.210600126 |
| [13] | 高振卓, 王志海, 刘海洋. 嵌入典型时间序列特征的随机Shapelet森林算法 Random Shapelet Forest Algorithm Embedded with Canonical Time Series Features 计算机科学, 2022, 49(7): 40-49. https://doi.org/10.11896/jsjkx.210700226 |
| [14] | 杨炳新, 郭艳蓉, 郝世杰, 洪日昌. 基于数据增广和模型集成策略的图神经网络在抑郁症识别上的应用 Application of Graph Neural Network Based on Data Augmentation and Model Ensemble in Depression Recognition 计算机科学, 2022, 49(7): 57-63. https://doi.org/10.11896/jsjkx.210800070 |
| [15] | 张洪博, 董力嘉, 潘玉彪, 萧宗志, 张惠臻, 杜吉祥. 视频理解中的动作质量评估方法综述 Survey on Action Quality Assessment Methods in Video Understanding 计算机科学, 2022, 49(7): 79-88. https://doi.org/10.11896/jsjkx.210600028 |
|
||
首页