Solving Machine Learning Problems

• URL: http://arxiv.org/abs/2107.01238v1
• Date: Fri, 2 Jul 2021 18:52:50 GMT
• Title: Solving Machine Learning Problems
• Authors: Sunny Tran, Pranav Krishna, Ishan Pakuwal, Prabhakar Kafle, Nikhil Singh, Jayson Lynch, Iddo Drori
• Abstract summary: 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. 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%.
• Score: 0.315565869552558
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• The Clock and the Pizza: Two Stories in Mechanistic Explanation of Neural Networks [59.26515696183751]
  We show that algorithm discovery in neural networks is sometimes more complex. We show that even simple learning problems can admit a surprising diversity of solutions.
  arXiv  Detail & Related papers  (2023-06-30T17:59:13Z)
• Are Deep Neural Networks SMARTer than Second Graders? [85.60342335636341]
  We evaluate the abstraction, deduction, and generalization abilities of neural networks in solving visuo-linguistic puzzles designed for children in the 6--8 age group. Our dataset consists of 101 unique puzzles; each puzzle comprises a picture question, and their solution needs a mix of several elementary skills, including arithmetic, algebra, and spatial reasoning. Experiments reveal that while powerful deep models offer reasonable performances on puzzles in a supervised setting, they are not better than random accuracy when analyzed for generalization.
  arXiv  Detail & Related papers  (2022-12-20T04:33:32Z)
• From Human Days to Machine Seconds: Automatically Answering and Generating Machine Learning Final Exams [10.25071232250652]
  A final exam in machine learning at a top institution such as MIT, Harvard, or Cornell typically takes faculty days to write, and students hours to solve. We demonstrate that large language models pass machine learning finals at a human level, on finals available online after the models were trained, and automatically generate new human-quality final exam questions in seconds.
  arXiv  Detail & Related papers  (2022-06-11T06:38:06Z)
• Solving Linear Algebra by Program Synthesis [1.0660480034605238]
  We solve MIT's Linear Algebra 18.06 course and Columbia University's Computational Linear Algebra COMS3251 courses with perfect accuracy by interactive program synthesis. This surprisingly strong result is achieved by turning the course questions into programming tasks and then running the programs to produce the correct answers.
  arXiv  Detail & Related papers  (2021-11-16T01:16:43Z)
• MixQG: Neural Question Generation with Mixed Answer Types [54.23205265351248]
  We propose a neural question generator, MixQG, to bridge this gap. We combine 9 question answering datasets with diverse answer types, including yes/no, multiple-choice, extractive, and abstractive answers. Our model outperforms existing work in both seen and unseen domains.
  arXiv  Detail & Related papers  (2021-10-15T16:03:40Z)
• Reservoir Stack Machines [77.12475691708838]
  Memory-augmented neural networks equip a recurrent neural network with an explicit memory to support tasks that require information storage. We introduce the reservoir stack machine, a model which can provably recognize all deterministic context-free languages. Our results show that the reservoir stack machine achieves zero error, even on test sequences longer than the training data.
  arXiv  Detail & Related papers  (2021-05-04T16:50:40Z)
• Conditional physics informed neural networks [85.48030573849712]
  We introduce conditional PINNs (physics informed neural networks) for estimating the solution of classes of eigenvalue problems. We show that a single deep neural network can learn the solution of partial differential equations for an entire class of problems.
  arXiv  Detail & Related papers  (2021-04-06T18:29:14Z)
• Interpretable Machine Learning: Fundamental Principles and 10 Grand Challenges [27.87985973854223]
  Interpretability in machine learning (ML) is crucial for high stakes decisions and troubleshooting. In this work, we provide fundamental principles for interpretable ML, and dispel common misunderstandings. We identify 10 technical challenge areas in interpretable machine learning and provide history and background on each problem.
  arXiv  Detail & Related papers  (2021-03-20T21:58:27Z)
• A Neural Question Answering System for Basic Questions about Subroutines [32.98355443690782]
  A question answering (QA) system is a type of conversational AI that generates natural language answers to questions posed by human users. We take initial steps to bringing state-of-the-art neural technologies to Software Engineering applications by designing a context-based QA system.
  arXiv  Detail & Related papers  (2021-01-11T16:18:52Z)
• Few-Shot Complex Knowledge Base Question Answering via Meta Reinforcement Learning [55.08037694027792]
  Complex question-answering (CQA) involves answering complex natural-language questions on a knowledge base (KB) The conventional neural program induction (NPI) approach exhibits uneven performance when the questions have different types. This paper proposes a meta-reinforcement learning approach to program induction in CQA to tackle the potential distributional bias in questions.
  arXiv  Detail & Related papers  (2020-10-29T18:34:55Z)
• A Novel Update Mechanism for Q-Networks Based On Extreme Learning Machines [0.6445605125467573]
  Extreme Q-Learning Machine (EQLM) is applied to a reinforcement learning problem in the same manner as gradient based updates. We compare its performance to a typical Q-Network on the cart-pole task. We show EQLM has similar long-term learning performance to a Q-Network.
  arXiv  Detail & Related papers  (2020-06-04T16:16:13Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.