148 lines
6.6 KiB
BibTeX
148 lines
6.6 KiB
BibTeX
|
|
|
|
@inproceedings{gralinski-etal-2019-geval,
|
|
title = "{GE}val: Tool for Debugging {NLP} Datasets and Models",
|
|
author = "Grali{\'n}ski, Filip and
|
|
Wr{\'o}blewska, Anna and
|
|
Stanis{\l}awek, Tomasz and
|
|
Grabowski, Kamil and
|
|
G{\'o}recki, Tomasz",
|
|
booktitle = "Proceedings of the 2019 ACL Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP",
|
|
month = aug,
|
|
year = "2019",
|
|
address = "Florence, Italy",
|
|
publisher = "Association for Computational Linguistics",
|
|
url = "https://www.aclweb.org/anthology/W19-4826",
|
|
pages = "254--262",
|
|
abstract = "This paper presents a simple but general and effective method to debug the output of machine learning (ML) supervised models, including neural networks. The algorithm looks for features that lower the evaluation metric in such a way that it cannot be ascribed to chance (as measured by their p-values). Using this method {--} implemented as MLEval tool {--} you can find: (1) anomalies in test sets, (2) issues in preprocessing, (3) problems in the ML model itself. It can give you an insight into what can be improved in the datasets and/or the model. The same method can be used to compare ML models or different versions of the same model. We present the tool, the theory behind it and use cases for text-based models of various types.",
|
|
}
|
|
|
|
@incollection {gonito2016,
|
|
title = {Gonito.net -- Open Platform for Research Competition, Cooperation and Reproducibility},
|
|
author = "Grali{\'n}ski, Filip and Jaworski, Rafa{\l} and Borchmann, {\L}ukasz and Wierzcho{\'n}, Piotr",
|
|
editor = "Branco, António and Calzolari , Nicoletta and Choukri, Khalid",
|
|
booktitle = {Proceedings of the 4REAL Workshop: Workshop on Research Results Reproducibility and Resources Citation in Science and Technology of Language},
|
|
year = "2016",
|
|
pages = "13-20"
|
|
}
|
|
|
|
@article{Overview,
|
|
author = {Simon, Annina and Deo, Mahima and Selvam, Venkatesan and Babu, Ramesh},
|
|
year = {2016},
|
|
month = {01},
|
|
pages = {22-24},
|
|
title = {An Overview of Machine Learning and its Applications},
|
|
volume = {Volume},
|
|
journal = {International Journal of Electrical Sciences \& Engineering}
|
|
}
|
|
|
|
@inproceedings{inproceedings,
|
|
author = {Read, Jesse and Bifet, Albert and Pfahringer, Bernhard and Holmes, Geoff},
|
|
year = {2012},
|
|
month = {10},
|
|
pages = {313-323},
|
|
title = {Batch-Incremental versus Instance-Incremental Learning in Dynamic and Evolving Data},
|
|
isbn = {978-3-642-34155-7},
|
|
doi = {10.1007/978-3-642-34156-4_29}
|
|
}
|
|
|
|
@article{drzewadecyzyjne,
|
|
author = {Rokach, Lior and Maimon, Oded},
|
|
year = {2005},
|
|
month = {12},
|
|
pages = {476 - 487},
|
|
title = {Top-Down Induction of Decision Trees Classifiers—A Survey},
|
|
volume = {35},
|
|
journal = {Systems, Man, and Cybernetics, Part C: Applications and Reviews, IEEE Transactions on},
|
|
doi = {10.1109/TSMCC.2004.843247}
|
|
}
|
|
|
|
@article{Srimani2015PerformanceAO,
|
|
title={Performance analysis of Hoeffding trees in data streams by using massive online analysis framework},
|
|
author={P. Srimani and Malini M. Patil},
|
|
journal={Int. J. Data Min. Model. Manag.},
|
|
year={2015},
|
|
volume={7},
|
|
pages={293-313}
|
|
}
|
|
|
|
@article{Lim2004ACO,
|
|
title={A Comparison of Prediction Accuracy, Complexity, and Training Time of Thirty-Three Old and New Classification Algorithms},
|
|
author={T. Lim and W. Loh and Yu-Shan Shih},
|
|
journal={Machine Learning},
|
|
year={2004},
|
|
volume={40},
|
|
pages={203-228}
|
|
}
|
|
|
|
@article{conceptdrift,
|
|
author = {Hashmani, Manzoor and Syed, Muslim and Rehman, Mobashar and Inoue, Atsushi},
|
|
year = {2020},
|
|
month = {01},
|
|
pages = {1-16},
|
|
title = {Concept Drift Evolution In Machine Learning Approaches: A Systematic Literature Review},
|
|
volume = {13},
|
|
journal = {International Journal on Smart Sensing and Intelligent Systems},
|
|
doi = {10.21307/ijssis-2020-029}
|
|
}
|
|
|
|
@InProceedings{comparision,
|
|
author="Burlutskiy, Nikolay
|
|
and Petridis, Miltos
|
|
and Fish, Andrew
|
|
and Chernov, Alexey
|
|
and Ali, Nour",
|
|
editor="Bramer, Max
|
|
and Petridis, Miltos",
|
|
title="An Investigation on Online Versus Batch Learning in Predicting User Behaviour",
|
|
booktitle="Research and Development in Intelligent Systems XXXIII",
|
|
year="2016",
|
|
publisher="Springer International Publishing",
|
|
address="Cham",
|
|
pages="135--149",
|
|
abstract="An investigation on how to produce a fast and accurate prediction of user behaviour on the Web is conducted. First, the problem of predicting user behaviour as a classification task is formulated and then the main problems of such real-time predictions are specified: the accuracy and time complexity of the prediction. Second, a method for comparison of online and batch (offline) algorithms used for user behaviour prediction is proposed. Last, the performance of these algorithms using the data from a popular question and answer platform, Stack Overflow, is empirically explored. It is demonstrated that a simple online learning algorithm outperforms state-of-the-art batch algorithms and performs as well as a deep learning algorithm, Deep Belief Networks. The proposed method for comparison of online and offline algorithms as well as the provided experimental evidence can be used for choosing a machine learning set-up for predicting user behaviour on the Web in scenarios where the accuracy and the time performance are of main concern.",
|
|
isbn="978-3-319-47175-4"
|
|
}
|
|
|
|
@inproceedings{comp,
|
|
author = {Carvalho, Vitor and Cohen, William},
|
|
year = {2006},
|
|
month = {01},
|
|
pages = {548-553},
|
|
title = {Single-pass online learning: Performance, voting schemes and online feature selection},
|
|
volume = {2006},
|
|
journal = {Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining},
|
|
doi = {10.1145/1150402.1150466}
|
|
}
|
|
|
|
@image{cross_val,
|
|
title = {https://medium.com/@eijaz/holdout-vs-cross-validation-in-machine-learning-7637112d3f8f},
|
|
url = {https://medium.com/@eijaz/holdout-vs-cross-validation-in-machine-learning-7637112d3f8f}
|
|
}
|
|
|
|
@image{confus,
|
|
title = {https://towardsdatascience.com/performance-metrics-confusion-matrix-precision-recall-and-f1-score-a8fe076a2262},
|
|
url = {https://towardsdatascience.com/performance-metrics-confusion-matrix-precision-recall-and-f1-score-a8fe076a2262}
|
|
}
|
|
|
|
@article{univ_kaggle,
|
|
title = {https://www.kaggle.com/longnguyen2306/germany-universities-reviews-and-recommendation},
|
|
url = {https://www.kaggle.com/longnguyen2306/germany-universities-reviews-and-recommendation}
|
|
}
|
|
|
|
@inproceedings{Jagirdar2018OnlineML,
|
|
title={Online Machine Learning Algorithms Review and Comparison in Healthcare},
|
|
author={N. Jagirdar},
|
|
year={2018}
|
|
}
|
|
|
|
@data{DVN/0U9Z9F_2018,
|
|
author = {Kulkarni, Rohit},
|
|
publisher = {Harvard Dataverse},
|
|
title = {{News Headlines of Ireland}},
|
|
UNF = {UNF:6:Ce4G0lq6wePPaBv5MZ8D9w==},
|
|
year = {2018},
|
|
version = {V2},
|
|
doi = {10.7910/DVN/0U9Z9F},
|
|
url = {https://doi.org/10.7910/DVN/0U9Z9F}
|
|
} |