Learning by Passing Tests, with Application to Neural Architecture Search

• URL: http://arxiv.org/abs/2011.15102v2
• Date: Fri, 12 Mar 2021 03:43:01 GMT
• Title: Learning by Passing Tests, with Application to Neural Architecture Search
• Authors: Xuefeng Du, Haochen Zhang, Pengtao Xie
• Abstract summary: We propose a novel learning approach called learning by passing tests. A tester model creates increasingly more-difficult tests to evaluate a learner model. The learner tries to continuously improve its learning ability so that it can successfully pass however difficult tests created by the tester.
• Score: 19.33620150924791
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Learning through tests is a broadly used methodology in human learning and shows great effectiveness in improving learning outcome: a sequence of tests are made with increasing levels of difficulty; the learner takes these tests to identify his/her weak points in learning and continuously addresses these weak points to successfully pass these tests. We are interested in investigating whether this powerful learning technique can be borrowed from humans to improve the learning abilities of machines. We propose a novel learning approach called learning by passing tests (LPT). In our approach, a tester model creates increasingly more-difficult tests to evaluate a learner model. The learner tries to continuously improve its learning ability so that it can successfully pass however difficult tests created by the tester. We propose a multi-level optimization framework to formulate LPT, where the tester learns to create difficult and meaningful tests and the learner learns to pass these tests. We develop an efficient algorithm to solve the LPT problem. Our method is applied for neural architecture search and achieves significant improvement over state-of-the-art baselines on CIFAR-100, CIFAR-10, and ImageNet.

Related papers

• Historical Test-time Prompt Tuning for Vision Foundation Models [99.96912440427192]
  HisTPT is a Historical Test-time Prompt Tuning technique that memorizes the useful knowledge of the learnt test samples. HisTPT achieves superior prompt tuning performance consistently while handling different visual recognition tasks.
  arXiv  Detail & Related papers  (2024-10-27T06:03:15Z)
• A Block-Based Testing Framework for Scratch [9.390562437823078]
  We introduce a new category of blocks in Scratch that enables the creation of automated tests. With these blocks, students and teachers alike can create tests and receive feedback directly within the Scratch environment.
  arXiv  Detail & Related papers  (2024-10-11T14:11:26Z)
• Implicit assessment of language learning during practice as accurate as explicit testing [0.5749787074942512]
  We use Item Response Theory (IRT) in computer-aided language learning for assessment of student ability in two contexts. We first aim to replace exhaustive tests with efficient but accurate adaptive tests. Second, we explore whether we can accurately estimate learner ability directly from the context of practice with exercises, without testing.
  arXiv  Detail & Related papers  (2024-09-24T14:40:44Z)
• Survey of Computerized Adaptive Testing: A Machine Learning Perspective [66.26687542572974]
  Computerized Adaptive Testing (CAT) provides an efficient and tailored method for assessing the proficiency of examinees. This paper aims to provide a machine learning-focused survey on CAT, presenting a fresh perspective on this adaptive testing method.
  arXiv  Detail & Related papers  (2024-03-31T15:09:47Z)
• RLIF: Interactive Imitation Learning as Reinforcement Learning [56.997263135104504]
  We show how off-policy reinforcement learning can enable improved performance under assumptions that are similar but potentially even more practical than those of interactive imitation learning. Our proposed method uses reinforcement learning with user intervention signals themselves as rewards. This relaxes the assumption that intervening experts in interactive imitation learning should be near-optimal and enables the algorithm to learn behaviors that improve over the potential suboptimal human expert.
  arXiv  Detail & Related papers  (2023-11-21T21:05:21Z)
• Towards Informed Design and Validation Assistance in Computer Games Using Imitation Learning [65.12226891589592]
  This paper proposes a new approach to automated game validation and testing. Our method leverages a data-driven imitation learning technique, which requires little effort and time and no knowledge of machine learning or programming.
  arXiv  Detail & Related papers  (2022-08-15T11:08:44Z)
• ALBench: A Framework for Evaluating Active Learning in Object Detection [102.81795062493536]
  This paper contributes an active learning benchmark framework named as ALBench for evaluating active learning in object detection. Developed on an automatic deep model training system, this ALBench framework is easy-to-use, compatible with different active learning algorithms, and ensures the same training and testing protocols.
  arXiv  Detail & Related papers  (2022-07-27T07:46:23Z)
• Learning from Mistakes -- A Framework for Neural Architecture Search [13.722450738258015]
  We propose a novel machine learning method called Learning From Mistakes (LFM) LFM improves the learner's ability to learn by focusing more on the mistakes during revision. We apply the LFM framework to neural architecture search on CIFAR-10, CIFAR-100, and Imagenet.
  arXiv  Detail & Related papers  (2021-11-11T18:04:07Z)
• Learning by Teaching, with Application to Neural Architecture Search [10.426533624387305]
  We propose a novel ML framework referred to as learning by teaching (LBT) In LBT, a teacher model improves itself by teaching a student model to learn well. Based on how the student performs on a validation dataset, the teacher re-learns its model and re-teaches the student until the student achieves great validation performance.
  arXiv  Detail & Related papers  (2021-03-11T23:50:38Z)
• Deep Reinforcement Learning for Adaptive Learning Systems [4.8685842576962095]
  We formulate the problem of how to find an individualized learning plan based on learner's latent traits. We apply a model-free deep reinforcement learning algorithm that can effectively find the optimal learning policy. We also develop a transition model estimator that emulates the learner's learning process using neural networks.
  arXiv  Detail & Related papers  (2020-04-17T18:04:03Z)
• Rethinking Few-Shot Image Classification: a Good Embedding Is All You Need? [72.00712736992618]
  We show that a simple baseline: learning a supervised or self-supervised representation on the meta-training set, outperforms state-of-the-art few-shot learning methods. An additional boost can be achieved through the use of self-distillation. We believe that our findings motivate a rethinking of few-shot image classification benchmarks and the associated role of meta-learning algorithms.
  arXiv  Detail & Related papers  (2020-03-25T17:58:42Z)

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.