Teaching Key Machine Learning Principles Using Anti-learning Datasets

Chris Roadknight; Prapa Rattadilok; Uwe Aickelin

doi:10.1109/TALE.2018.8615252

Teaching Key Machine Learning Principles Using Anti-learning Datasets

Chris Roadknight, Prapa Rattadilok, Uwe Aickelin

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

1 Citation (Scopus)

Abstract

Much of the teaching of machine learning focuses on iterative hill-climbing approaches and the use of local knowledge to gain information leading to local or global maxima. In this paper we advocate the teaching of alternative methods of generalising to the best possible solution, including a method called anti-learning. By using simple teaching methods, students can achieve a deeper understanding of the importance of validation on data excluded from the training process and that each problem requires its own methods to solve. We also exemplify the requirement to train a model using sufficient data by showing that different granularities of cross-validation can yield very different results.

Original language	English
Title of host publication	Proceedings of 2018 IEEE International Conference on Teaching, Assessment, and Learning for Engineering, TALE 2018
Editors	Mark J.W. Lee, Sasha Nikolic, Gary K.W. Wong, Jun Shen, Montserrat Ros, Leon C. U. Lei, Neelakantam Venkatarayalu
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
Pages	960-964
Number of pages	5
ISBN (Electronic)	9781538665220
DOIs	https://doi.org/10.1109/TALE.2018.8615252
Publication status	Published - 16 Jan 2019
Event	2018 IEEE International Conference on Teaching, Assessment, and Learning for Engineering, TALE 2018 - Wollongong, Australia Duration: 4 Dec 2018 → 7 Dec 2018

Publication series

Name	Proceedings of 2018 IEEE International Conference on Teaching, Assessment, and Learning for Engineering, TALE 2018

Conference

Conference	2018 IEEE International Conference on Teaching, Assessment, and Learning for Engineering, TALE 2018
Country/Territory	Australia
City	Wollongong
Period	4/12/18 → 7/12/18

Keywords

anti-learning
exclusive-or
hadamard
machine learning

Access to Document

10.1109/TALE.2018.8615252Licence: Unspecified

Cite this

Roadknight, C., Rattadilok, P., & Aickelin, U. (2019). Teaching Key Machine Learning Principles Using Anti-learning Datasets. In M. J. W. Lee, S. Nikolic, G. K. W. Wong, J. Shen, M. Ros, L. C. U. Lei, & N. Venkatarayalu (Eds.), Proceedings of 2018 IEEE International Conference on Teaching, Assessment, and Learning for Engineering, TALE 2018 (pp. 960-964). Article 8615252 (Proceedings of 2018 IEEE International Conference on Teaching, Assessment, and Learning for Engineering, TALE 2018). Institute of Electrical and Electronics Engineers (IEEE). https://doi.org/10.1109/TALE.2018.8615252

Roadknight, Chris ; Rattadilok, Prapa ; Aickelin, Uwe. / Teaching Key Machine Learning Principles Using Anti-learning Datasets. Proceedings of 2018 IEEE International Conference on Teaching, Assessment, and Learning for Engineering, TALE 2018. editor / Mark J.W. Lee ; Sasha Nikolic ; Gary K.W. Wong ; Jun Shen ; Montserrat Ros ; Leon C. U. Lei ; Neelakantam Venkatarayalu. Institute of Electrical and Electronics Engineers (IEEE), 2019. pp. 960-964 (Proceedings of 2018 IEEE International Conference on Teaching, Assessment, and Learning for Engineering, TALE 2018).

@inproceedings{2b0c8ec621524b82aa58feb6280bcef1,

title = "Teaching Key Machine Learning Principles Using Anti-learning Datasets",

abstract = "Much of the teaching of machine learning focuses on iterative hill-climbing approaches and the use of local knowledge to gain information leading to local or global maxima. In this paper we advocate the teaching of alternative methods of generalising to the best possible solution, including a method called anti-learning. By using simple teaching methods, students can achieve a deeper understanding of the importance of validation on data excluded from the training process and that each problem requires its own methods to solve. We also exemplify the requirement to train a model using sufficient data by showing that different granularities of cross-validation can yield very different results.",

keywords = "anti-learning, exclusive-or, hadamard, machine learning",

author = "Chris Roadknight and Prapa Rattadilok and Uwe Aickelin",

note = "{\textcopyright} 2018 IEEE.; 2018 IEEE International Conference on Teaching, Assessment, and Learning for Engineering, TALE 2018 ; Conference date: 04-12-2018 Through 07-12-2018",

year = "2019",

month = jan,

day = "16",

doi = "10.1109/TALE.2018.8615252",

language = "English",

series = "Proceedings of 2018 IEEE International Conference on Teaching, Assessment, and Learning for Engineering, TALE 2018",

publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

pages = "960--964",

editor = "Lee, {Mark J.W.} and Sasha Nikolic and Wong, {Gary K.W.} and Jun Shen and Montserrat Ros and Lei, {Leon C. U.} and Neelakantam Venkatarayalu",

booktitle = "Proceedings of 2018 IEEE International Conference on Teaching, Assessment, and Learning for Engineering, TALE 2018",

address = "United States",

}

Roadknight, C, Rattadilok, P & Aickelin, U 2019, Teaching Key Machine Learning Principles Using Anti-learning Datasets. in MJW Lee, S Nikolic, GKW Wong, J Shen, M Ros, LCU Lei & N Venkatarayalu (eds), Proceedings of 2018 IEEE International Conference on Teaching, Assessment, and Learning for Engineering, TALE 2018., 8615252, Proceedings of 2018 IEEE International Conference on Teaching, Assessment, and Learning for Engineering, TALE 2018, Institute of Electrical and Electronics Engineers (IEEE), pp. 960-964, 2018 IEEE International Conference on Teaching, Assessment, and Learning for Engineering, TALE 2018, Wollongong, Australia, 4/12/18. https://doi.org/10.1109/TALE.2018.8615252

Teaching Key Machine Learning Principles Using Anti-learning Datasets. / Roadknight, Chris; Rattadilok, Prapa; Aickelin, Uwe.
Proceedings of 2018 IEEE International Conference on Teaching, Assessment, and Learning for Engineering, TALE 2018. ed. / Mark J.W. Lee; Sasha Nikolic; Gary K.W. Wong; Jun Shen; Montserrat Ros; Leon C. U. Lei; Neelakantam Venkatarayalu. Institute of Electrical and Electronics Engineers (IEEE), 2019. p. 960-964 8615252 (Proceedings of 2018 IEEE International Conference on Teaching, Assessment, and Learning for Engineering, TALE 2018).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Teaching Key Machine Learning Principles Using Anti-learning Datasets

AU - Roadknight, Chris

AU - Rattadilok, Prapa

AU - Aickelin, Uwe

PY - 2019/1/16

Y1 - 2019/1/16

N2 - Much of the teaching of machine learning focuses on iterative hill-climbing approaches and the use of local knowledge to gain information leading to local or global maxima. In this paper we advocate the teaching of alternative methods of generalising to the best possible solution, including a method called anti-learning. By using simple teaching methods, students can achieve a deeper understanding of the importance of validation on data excluded from the training process and that each problem requires its own methods to solve. We also exemplify the requirement to train a model using sufficient data by showing that different granularities of cross-validation can yield very different results.

AB - Much of the teaching of machine learning focuses on iterative hill-climbing approaches and the use of local knowledge to gain information leading to local or global maxima. In this paper we advocate the teaching of alternative methods of generalising to the best possible solution, including a method called anti-learning. By using simple teaching methods, students can achieve a deeper understanding of the importance of validation on data excluded from the training process and that each problem requires its own methods to solve. We also exemplify the requirement to train a model using sufficient data by showing that different granularities of cross-validation can yield very different results.

KW - anti-learning

KW - exclusive-or

KW - hadamard

KW - machine learning

UR - http://www.scopus.com/inward/record.url?scp=85062058668&partnerID=8YFLogxK

U2 - 10.1109/TALE.2018.8615252

DO - 10.1109/TALE.2018.8615252

M3 - Conference contribution

AN - SCOPUS:85062058668

T3 - Proceedings of 2018 IEEE International Conference on Teaching, Assessment, and Learning for Engineering, TALE 2018

SP - 960

EP - 964

BT - Proceedings of 2018 IEEE International Conference on Teaching, Assessment, and Learning for Engineering, TALE 2018

A2 - Lee, Mark J.W.

A2 - Nikolic, Sasha

A2 - Wong, Gary K.W.

A2 - Shen, Jun

A2 - Ros, Montserrat

A2 - Lei, Leon C. U.

A2 - Venkatarayalu, Neelakantam

PB - Institute of Electrical and Electronics Engineers (IEEE)

T2 - 2018 IEEE International Conference on Teaching, Assessment, and Learning for Engineering, TALE 2018

Y2 - 4 December 2018 through 7 December 2018

ER -

Roadknight C, Rattadilok P, Aickelin U. Teaching Key Machine Learning Principles Using Anti-learning Datasets. In Lee MJW, Nikolic S, Wong GKW, Shen J, Ros M, Lei LCU, Venkatarayalu N, editors, Proceedings of 2018 IEEE International Conference on Teaching, Assessment, and Learning for Engineering, TALE 2018. Institute of Electrical and Electronics Engineers (IEEE). 2019. p. 960-964. 8615252. (Proceedings of 2018 IEEE International Conference on Teaching, Assessment, and Learning for Engineering, TALE 2018). doi: 10.1109/TALE.2018.8615252

Teaching Key Machine Learning Principles Using Anti-learning Datasets

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this