Solving Machine Learning Problems
Can a machine learn Machine Learning? This work trains a machine learning model to solve machine learning problems from a University undergraduate level course. We generate a new training set of questions and answers consisting of course exercises, homework, and quiz questions from MIT’s 6.036 Intro...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis |
| Published: |
Massachusetts Institute of Technology
2022
|
| Online Access: | https://hdl.handle.net/1721.1/143412 https://orcid.org/ 0000-0002-6930-0349 |
| _version_ | 1826194531979100160 |
|---|---|
| author | Tran, Sunny |
| author2 | Drori, Iddo |
| author_facet | Drori, Iddo Tran, Sunny |
| author_sort | Tran, Sunny |
| collection | MIT |
| description | Can a machine learn Machine Learning? This work trains a machine learning model to solve machine learning problems from a University undergraduate level course. We generate a new training set of questions and answers consisting of course exercises, homework, and quiz questions from MIT’s 6.036 Introduction to Machine Learning course and train a machine learning model to answer these questions. Our system demonstrates an overall accuracy of 96% for open-response questions and 97% for multiple-choice questions, compared with MIT students’ average of 93%, achieving grade A performance in the course, all in real-time. Questions cover all 12 topics taught in the course, excluding coding questions or questions with images. Topics include: (i) basic machine learning principles; (ii) perceptrons; (iii) feature extraction and selection; (iv) logistic regression; (v) regression; (vi) neural networks; (vii) advanced neural networks; (viii) convolutional neural networks; (ix) recurrent neural networks; (x) state machines and MDPs; (xi) reinforcement learning; and (xii) decision trees. Our system uses Transformer models within an encoder-decoder architecture with graph and tree representations. An important aspect of our approach is a data-augmentation scheme for generating new example problems. We also train a machine learning model to generate problem hints. Thus, our system automatically generates new questions across topics, answers both open-response questions and multiple-choice questions, classifies problems, and generates problem hints, pushing the envelope of AI for STEM education. |
| first_indexed | 2024-09-23T09:57:32Z |
| format | Thesis |
| id | mit-1721.1/143412 |
| institution | Massachusetts Institute of Technology |
| last_indexed | 2024-09-23T09:57:32Z |
| publishDate | 2022 |
| publisher | Massachusetts Institute of Technology |
| record_format | dspace |
| spelling | mit-1721.1/1434122022-06-16T03:45:42Z Solving Machine Learning Problems Tran, Sunny Drori, Iddo Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science Can a machine learn Machine Learning? This work trains a machine learning model to solve machine learning problems from a University undergraduate level course. We generate a new training set of questions and answers consisting of course exercises, homework, and quiz questions from MIT’s 6.036 Introduction to Machine Learning course and train a machine learning model to answer these questions. Our system demonstrates an overall accuracy of 96% for open-response questions and 97% for multiple-choice questions, compared with MIT students’ average of 93%, achieving grade A performance in the course, all in real-time. Questions cover all 12 topics taught in the course, excluding coding questions or questions with images. Topics include: (i) basic machine learning principles; (ii) perceptrons; (iii) feature extraction and selection; (iv) logistic regression; (v) regression; (vi) neural networks; (vii) advanced neural networks; (viii) convolutional neural networks; (ix) recurrent neural networks; (x) state machines and MDPs; (xi) reinforcement learning; and (xii) decision trees. Our system uses Transformer models within an encoder-decoder architecture with graph and tree representations. An important aspect of our approach is a data-augmentation scheme for generating new example problems. We also train a machine learning model to generate problem hints. Thus, our system automatically generates new questions across topics, answers both open-response questions and multiple-choice questions, classifies problems, and generates problem hints, pushing the envelope of AI for STEM education. M.Eng. 2022-06-15T13:19:04Z 2022-06-15T13:19:04Z 2022-02 2022-02-22T18:32:28.679Z Thesis https://hdl.handle.net/1721.1/143412 https://orcid.org/ 0000-0002-6930-0349 In Copyright - Educational Use Permitted Copyright MIT http://rightsstatements.org/page/InC-EDU/1.0/ application/pdf Massachusetts Institute of Technology |
| spellingShingle | Tran, Sunny Solving Machine Learning Problems |
| title | Solving Machine Learning Problems |
| title_full | Solving Machine Learning Problems |
| title_fullStr | Solving Machine Learning Problems |
| title_full_unstemmed | Solving Machine Learning Problems |
| title_short | Solving Machine Learning Problems |
| title_sort | solving machine learning problems |
| url | https://hdl.handle.net/1721.1/143412 https://orcid.org/ 0000-0002-6930-0349 |
| work_keys_str_mv | AT transunny solvingmachinelearningproblems |