Theoretical and Natural Science
- The Open Access Proceedings Series for Conferences
Proceedings of the 2nd International Conference on Computing Innovation and Applied Physics (CONF-CIAP 2023)
Series Vol. 5 , 25 May 2023
Open
Access | Article
A Practical Significant Technic in Solving Overfitting: Regularization
* Author to whom correspondence should be addressed.
Abstract
The passage mainly discusses the solution to overfitting. Overfitting usually happens when people are training their machine learning models. When a model is overfitted, it only fits one particular dataset and misses most of the data points from another dataset. This problem affects the model's performance and makes it unable to use for its purpose. So how to solve this problem with significance and practical meaning? At the beginning of the passage, I will introduce some theoretical foundations for overfitting. Then I will define the concept of overfitting and show an example of overfitting in the machine learning model. After that, I will tell you how to pick the correct model with the testing set. Then, the passage focuses on the discussion of regularization, which is a helpful technique for solving overfitting. And I will compare the L1 and l2 regularization to help you find the suitable one.
Keywords
Machine Learning Model, Overfitting, Regularization, L1 Norm, L2 Norm.
References
1. Catbug88@home: ~$. Introduction to Linear Algebra for Applied Machine Learning with Python. (n.d.). Retrieved October 23, 2022, from https://pabloinsente.github.io/intro-linear-algebra.
2. Serrano, L. G., & Thrun, S. (2021). Grokking Machine Learning. Manning Publications Co.
3. Tyagi, N. (n.d.). L2 vs L1 regularization in machine learning: Ridge and Lasso regularization. L2 vs L1 Regularization in Machine Learning | Ridge and Lasso Regularization. Retrieved October 23, 2022, from https://www.analyticssteps.com/blogs/l2-and-l1-regularization-machine-learning
Data Availability
The datasets used and/or analyzed during the current study will be available from the authors upon reasonable request.
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. Authors who publish this series agree to the following terms:
1. Authors retain copyright and grant the series right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this series.
2. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the series's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this series.
3. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See Open Access Instruction).
- Volume Title
- Proceedings of the 2nd International Conference on Computing Innovation and Applied Physics (CONF-CIAP 2023)
- ISBN (Print)
- 978-1-915371-53-9
- ISBN (Online)
- 978-1-915371-54-6
- Published Date
- 25 May 2023
- Series
- Theoretical and Natural Science
- ISSN (Print)
- 2753-8818
- ISSN (Online)
- 2753-8826
- DOI
- 10.54254/2753-8818/5/20230433
- Copyright
- © 2023 The Author(s)
- Open Access
- This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited