請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/93922完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 蔣正偉 | zh_TW |
| dc.contributor.advisor | Cheng-Wei Chiang | en |
| dc.contributor.author | 陳宗恩 | zh_TW |
| dc.contributor.author | Zong-En Chen | en |
| dc.date.accessioned | 2024-08-09T16:26:43Z | - |
| dc.date.available | 2024-08-10 | - |
| dc.date.copyright | 2024-08-09 | - |
| dc.date.issued | 2024 | - |
| dc.date.submitted | 2024-07-22 | - |
| dc.identifier.citation | [1] H. Beauchesne, Z.-E. Chen and C.-W. Chiang, Improving the performance of weak supervision searches using transfer and meta-learning, JHEP 02 (2024) 138 [2312.06152].
[2] PARTICLE DATA GROUP collaboration, Review of Particle Physics, PTEP 2022 (2022) 083C01. [3] Y.-C.J. Chen, C.-W. Chiang, G. Cottin and D. Shih, Boosted W and Z tagging with jet charge and deep learning, Phys. Rev. D 101 (2020) 053001 [1908.08256]. [4] E. Bernreuther, T. Finke, F. Kahlhoefer, M. Kr¨ amer and A. M¨ uck, Casting a graph net to catch dark showers, SciPost Phys. 10 (2021) 046 [2006.08639]. [5] S. Chang, T.-K. Chen and C.-W. Chiang, Distinguishing W′signals at hadron colliders using neural networks, Phys. Rev. D 103 (2021) 036016 [2007.14586]. [6] C.-W. Chiang, D. Shih and S.-F. Wei, VBF vs. GGF Higgs with Full-Event Deep Learning: Towards a Decay-Agnostic Tagger, Phys. Rev. D 107 (2023) 016014 [2209.05518]. [7] E.M. Metodiev, B. Nachman and J. Thaler, Classification without labels: Learning from mixed samples in high energy physics, JHEP 10 (2017) 174 [1708.02949]. [8] M. Farina, Y. Nakai and D. Shih, Searching for New Physics with Deep Autoencoders, Phys. Rev. D 101 (2020) 075021 [1808.08992]. [9] J. Batson, C.G. Haaf, Y. Kahn and D.A. Roberts, Topological Obstructions to Autoencoding, JHEP 04 (2021) 280 [2102.08380]. [10] B.M. Dillon, T. Plehn, C. Sauer and P. Sorrenson, Better Latent Spaces for Better Autoencoders, SciPost Phys. 11 (2021) 061 [2104.08291]. [11] ATLAS collaboration, Dijet resonance search with weak supervision using √s= 13 TeV ppcollisions in the ATLAS detector, Phys. Rev. Lett. 125 (2020) 131801 [2005.02983]. [12] J.H. Collins, P. Mart´ ın-Ramiro, B. Nachman and D. Shih, Comparing weak-and unsupervised methods for resonant anomaly detection, Eur. Phys. J. C 81 (2021) 617 [2104.02092]. [13] C.L. Cheng, G. Singh and B. Nachman, Incorporating Physical Priors into Weakly-Supervised Anomaly Detection, 2405.08889. [14] C. Li et al., Accelerating Resonance Searches via Signature-Oriented Pre-training, 2405.12972. [15] B.M. Dillon, L. Favaro, F. Feiden, T. Modak and T. Plehn, Anomalies, Representations, and Self-Supervision, 2301.04660. [16] J.H. Collins, K. Howe and B. Nachman, Anomaly Detection for Resonant New Physics with Machine Learning, Phys. Rev. Lett. 121 (2018) 241803 [1805.02664]. [17] T. Finke, M. Hein, G. Kasieczka, M. Kr¨ amer, A. M¨ uck, P. Prangchaikul et al., Back To The Roots: Tree-Based Algorithms for Weakly Supervised Anomaly Detection, 2309.13111. [18] M. Freytsis, M. Perelstein and Y.C. San, Anomaly Detection in Presence of Irrelevant Features, 2310.13057. [19] F.A. Dreyer, R. Grabarczyk and P.F. Monni, Leveraging universality of jet taggers through transfer learning, Eur. Phys. J. C 82 (2022) 564 [2203.06210]. [20] A. Chappell and L.H. Whitehead, Application of transfer learning to neutrino interaction classification, Eur. Phys. J. C 82 (2022) 1099 [2207.03139]. [21] M.P. Kuchera, R. Ramanujan, J.Z. Taylor, R.R. Strauss, D. Bazin, J. Bradt et al., Machine Learning Methods for Track Classification in the AT-TPC, Nucl. Instrum. Meth. A 940 (2019) 156 [1810.10350]. [22] W. Wei et al., Deep transfer learning for star cluster classification: I. application to the PHANGS–HST survey, Mon. Not. Roy. Astron. Soc. 493 (2020) 3178 [1909.02024]. [23] M. Eriksen et al., The PAU Survey: Photometric redshifts using transfer learning from simulations, Mon. Not. Roy. Astron. Soc. 497 (2020) 4565 [2004.07979]. [24] D. George, H. Shen and E.A. Huerta, Deep Transfer Learning: A new deep learning glitch classification method for advanced LIGO, 1706.07446. 5 [25] D. George, H. Shen and E.A. Huerta, Glitch Classification and Clustering for LIGO with Deep Transfer Learning, in NiPS Summer School 2017, 11, 2017 [1711.07468]. [26] T. Kishimoto, M. Morinaga, M. Saito and J. Tanaka, Application of transfer learning to event classification in collider physics, PoS ISGC2022 (2022) 016. [27] M.J. Dolan and A. Ore, Metalearning and data augmentation for mass-generalized jet taggers, Phys. Rev. D 105 (2022) 094030 [2111.06047]. [28] T. Hospedales, A. Antoniou, P. Micaelli and A. Storkey, Meta-learning in neural networks: A survey, IEEE Transactions on Pattern Analysis; Machine Intelligence 44 (2022) 5149. [29] L. Carloni, J. Rathsman and T. Sjostrand, Discerning Secluded Sector gauge structures, JHEP 04 (2011) 091 [1102.3795]. [30] L. Carloni and T. Sjostrand, Visible Effects of Invisible Hidden Valley Radiation, JHEP 09 (2010) 105 [1006.2911]. [31] G. Albouy et al., Theory, phenomenology, and experimental avenues for dark showers: a Snowmass 2021 report, Eur. Phys. J. C 82 (2022) 1132 [2203.09503]. [32] H. Beauchesne, E. Bertuzzo and G. Grilli Di Cortona, Dark matter in Hidden Valley models with stable and unstable light dark mesons, JHEP 04 (2019) 118 [1809.10152]. [33] E. Bernreuther, F. Kahlhoefer, M. Kr¨ amer and P. Tunney, Strongly interacting dark sectors in the early Universe and at the LHC through a simplified portal, JHEP 01 (2020) 162 [1907.04346]. [34] H. Beauchesne and G. Grilli di Cortona, Classification of dark pion multiplets as dark matter candidates and collider phenomenology, JHEP 02 (2020) 196 [1910.10724]. [35] CMS collaboration, Search for new particles decaying to a jet and an emerging jet, JHEP 02 (2019) 179 [1810.10069]. [36] CMS collaboration, Search for resonant production of strongly coupled dark matter in proton-proton collisions at 13 TeV, JHEP 06 (2022) 156 [2112.11125]. [37] ATLAS collaboration, Search for non-resonant production of semi-visible jets using Run 2 data in ATLAS, Phys. Lett. B 848 (2024) 138324 [2305.18037]. [38] ATLAS collaboration, Search for Resonant Production of Dark Quarks in the Dijet Final State with the ATLAS Detector, 2311.03944. [39] J. Alwall, R. Frederix, S. Frixione, V. Hirschi, F. Maltoni, O. Mattelaer et al., The automated computation of tree-level and next-to-leading order differential cross sections, and their matching to parton shower simulations, JHEP 07 (2014) 079 [1405.0301]. [40] R.D. Ball et al., Parton distributions with LHC data, Nucl. Phys. B 867 (2013) 244 [1207.1303]. [41] DELPHES 3 collaboration, DELPHES 3, A modular framework for fast simulation of a generic collider experiment, JHEP 02 (2014) 057 [1307.6346]. [42] M. Cacciari, G.P. Salam and G. Soyez, FastJet User Manual, Eur. Phys. J. C 72 (2012) 1896 [1111.6097]. [43] A.J. Larkoski, J. Thaler and W.J. Waalewijn, Gaining (Mutual) Information about Quark/Gluon Discrimination, JHEP 11 (2014) 129 [1408.3122]. [44] C.F. Berger, T. Kucs and G.F. Sterman, Event shape / energy flow correlations, Phys. Rev. D 68 (2003) 014012 [hep-ph/0303051]. [45] L.G. Almeida, S.J. Lee, G. Perez, G.F. Sterman, I. Sung and J. Virzi, Substructure of high-pT Jets at the LHC, Phys. Rev. D 79 (2009) 074017 [0807.0234]. [46] S.D. Ellis, C.K. Vermilion, J.R. Walsh, A. Hornig and C. Lee, Jet Shapes and Jet Algorithms in SCET, JHEP 11 (2010) 101 [1001.0014]. [47] CMS collaboration, Search for a Higgs Boson in the Decay Channel H →ZZ∗→q¯ qℓ−ℓ+ in ppCollisions at √s= 7 TeV, JHEP 04 (2012) 036 [1202.1416]. [48] P. Gras, S. H¨ oche, D. Kar, A. Larkoski, L. L¨ onnblad, S. Pl¨ atzer et al., Systematics of quark/gluon tagging, JHEP 07 (2017) 091 [1704.03878]. [49] J.R. Andersen et al., Les Houches 2015: Physics at TeV Colliders Standard Model Working Group Report, in 9th Les Houches Workshop on Physics at TeV Colliders, 5, 2016 [1605.04692]. [50] A. Butter et al., The Machine Learning landscape of top taggers, SciPost Phys. 7 (2019) 014 [1902.09914]. [51] L. de Oliveira, M. Kagan, L. Mackey, B. Nachman and A. Schwartzman, Jet-images — deep learning edition, JHEP 07 (2016) 069 [1511.05190]. [52] G. Kasieczka, T. Plehn, M. Russell and T. Schell, Deep-learning Top Taggers or The End of QCD?, JHEP 05 (2017) 006 [1701.08784]. [53] J. Neyman and E.S. Pearson, On the Problem of the Most Efficient Tests of Statistical Hypotheses, Phil. Trans. Roy. Soc. Lond. A 231 (1933) 289. [54] F. Chollet et al., “Keras.” https://keras.io, 2015. [55] M. Abadi et al., TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems, 1603.04467. [56] ATLAS collaboration, Formulae for Estimating Significance, 2020. [57] K. He, X. Zhang, S. Ren and J. Sun, Deep residual learning for image recognition, in Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 770–778, 2016. [58] O. Russakovsky, J. Deng, H. Su, J. Krause, S. Satheesh, S. Ma et al., Imagenet large scale visual recognition challenge, International journal of computer vision 115 (2015) 211. [59] J. Kirkpatrick, R. Pascanu, N. Rabinowitz, J. Veness, G. Desjardins, A.A. Rusu et al., Overcoming catastrophic forgetting in neural networks, Proceedings of the national academy of sciences 114 (2017) 3521. [60] M.D. Zeiler and R. Fergus, Visualizing and understanding convolutional networks, in Computer Vision–ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part I 13, pp. 818–833, Springer, 2014. [61] Q. Sun, Y. Liu, T.-S. Chua and B. Schiele, Meta-transfer learning for few-shot learning, 1812.02391. | - |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/93922 | - |
| dc.description.abstract | 弱監督搜尋在原理上具有以下兩個優點：既能夠在實驗數據上進行訓練，又能夠學習到獨特的信號特性。然而，由於在弱監督下成功訓練神經網絡可能需要大量的信號，因此這種搜尋策略的實際應用性受到嚴重限制。在本研究中，我們嘗試開發更高效和更智能的神經網絡，通過利用遷移學習和元學習來從較少的實驗數據信號中學習。其基本思路是首先在模擬數據上訓練神經網絡，學習關鍵概念並成為更高效的學習者。隨後，神經網絡再在實際數據上進行訓練，通過利用從模擬中獲得的知識和概念，期望能夠在學習中需要較少的信號。我們發現，遷移學習和元學習可以顯著提高弱監督搜尋的性能。 | zh_TW |
| dc.description.abstract | Weak supervision searches have in principle the advantages of both being able to train on experimental data and being able to learn distinctive signal properties. However, because successfully training a neural network under weak supervision can require a large amount of signal, the practical applicability of this search strategy is seriously limited. In this study, we try to develop more efficient and smarter neural networks that can learn from less signal in the experimental data by utilizing transfer learning and meta-learning. The general idea is to first train a neural network on simulations, learning critical concepts and becoming a more efficient learner. Subsequently, the neural network is trained on real data and, by exploiting the knowledge and concepts acquired from simulations, should hopefully require less signals to learn. We find that transfer and meta-learning can substantially improve the performance of weak supervision searches. | en |
| dc.description.provenance | Submitted by admin ntu (admin@lib.ntu.edu.tw) on 2024-08-09T16:26:42Z No. of bitstreams: 0 | en |
| dc.description.provenance | Made available in DSpace on 2024-08-09T16:26:43Z (GMT). No. of bitstreams: 0 | en |
| dc.description.tableofcontents | Abstract i
Contents ii List of Figures iv List of Tables ix Chapter 1 Introduction 1 Chapter 2 Events generation 7 Section 2.1 Signal and background generation 7 Section 2.2 Image preprocessing 13 Chapter 3 Classification without labels (CWoLa) 20 Section 3.1 Theoretical perspectives 20 Section 3.2 The implementation of CWoLa 22 Section 3.3 Discussion 23 Chapter 4 Transfer learning 30 Section 4.1 Introduction to transfer learning 30 Section 4.2 Implementation of Transfer Learning 32 Section 4.3 Discussion 34 Chapter 5 Meta learning 39 Section 5.1 Introduction to meta-transfer learning 39 Section 5.2 Implementation of meta-transfer learning 40 Section 5.3 Discussion 42 Chapter 6 Conclusion 50 Reference 52 | - |
| dc.language.iso | zh_TW | - |
| dc.subject | 機器學習 | zh_TW |
| dc.subject | 遷移學習 | zh_TW |
| dc.subject | 元學習 | zh_TW |
| dc.subject | 弱監督搜索 | zh_TW |
| dc.subject | Transfer leaning | en |
| dc.subject | Meta-learning | en |
| dc.subject | Machine learning | en |
| dc.subject | Weak supervision searches | en |
| dc.title | 利用遷移和元學習提升弱監督搜索效能 | zh_TW |
| dc.title | Improving the performance of weak supervision searches using transfer learning and meta-learning | en |
| dc.type | Thesis | - |
| dc.date.schoolyear | 112-2 | - |
| dc.description.degree | 碩士 | - |
| dc.contributor.oralexamcommittee | 陳傳仁;裴思達 | zh_TW |
| dc.contributor.oralexamcommittee | Chuan-Ren Chen;Stathes Paganis | en |
| dc.subject.keyword | 機器學習,遷移學習,元學習,弱監督搜索, | zh_TW |
| dc.subject.keyword | Machine learning,Transfer leaning,Meta-learning,Weak supervision searches, | en |
| dc.relation.page | 58 | - |
| dc.identifier.doi | 10.6342/NTU202401831 | - |
| dc.rights.note | 同意授權(全球公開) | - |
| dc.date.accepted | 2024-07-22 | - |
| dc.contributor.author-college | 理學院 | - |
| dc.contributor.author-dept | 物理學系 | - |
| 顯示於系所單位： | 物理學系 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| ntu-112-2.pdf | 2.88 MB | Adobe PDF | 檢視/開啟 |
系統中的文件，除了特別指名其著作權條款之外，均受到著作權保護，並且保留所有的權利。