Leveraging Failures to Enhance Hierarchical Concept Learning when Training and Testing are Limited
نویسندگان
چکیده
Hierarchical concept learning constructs higher-level concepts using previously learned prerequisite concepts. We are working in an especially challenging context where only a small number of training instances for each concept are provided to the learning system. This limited instruction forces even the most skillful learner to make assumptions about the concept being taught—assumptions that can be incorrect. Given this uncertainty, multiple candidates may be proposed for the concept, each stemming from different assumptions that are consistent with the training. We present a control strategy for managing the use of hypothesized concept candidates in higher-level learning. The strategy is based on three key ideas: 1) limiting prerequisitecandidate combinatorics by operating with a single selected candidate for each concept at any time, 2) using learning failure to select a different candidate for a direct or indirect prerequisite concept, and 3) using differences observed as candidates are used to guide candidate selection. We implemented and evaluated this novel Concept Candidate Management (CCM) strategy in MABLE, an electronic student that performs bootstrapped concept learning. Using the CCM strategy, MABLE learned concepts that were not successfully learned otherwise—without any additional training or testing and without any changes to learning algorithms.
منابع مشابه
Hierarchical Transfer Convolutional Neural Networks for Image Classification
In this paper, we address the issue of how to enhance the generalization performance of convolutional neural networks (CNN) in the early learning stage for image classification. This is motivated by real-time applications that require the generalization performance of CNN to be satisfactory within limited training time. In order to achieve this, a novel hierarchical transfer CNN framework is pr...
متن کاملAbsorptive Capability and Competitive Advantage: Some Insights from Indian Pharmaceutical Industry
Every firm learns through firm specific methods. This learning process is operationalized by firm’s knowledge management practices. Therefore, knowledge to result in successful learning should be assisted by a combinative framework which can enhance a firms’ absorptive capability. This in turn will play a decisive role for achieving competitive advantage. Current literature in strategic managem...
متن کاملThe effect of emotion regulation training in decreasing emotion failures and self-injurious behaviors among students suffering from specific learning disorder(SLD)
Background: A great deal of attention has been given to the study of learning disorders. Hence, the aim of this research was to study the effect of emotion regulation training in decreasing emotion failures and self-injurious behaviors among students suffering from specific learning disorder. Methods: This was an experimental study with the pre-test, post-test and a control group. Research p...
متن کاملHierarchical Functional Concepts for Knowledge Transfer among Reinforcement Learning Agents
This article introduces the notions of functional space and concept as a way of knowledge representation and abstraction for Reinforcement Learning agents. These definitions are used as a tool of knowledge transfer among agents. The agents are assumed to be heterogeneous; they have different state spaces but share a same dynamic, reward and action space. In other words, the agents are assumed t...
متن کاملDetecting Concept Drift in Data Stream Using Semi-Supervised Classification
Data stream is a sequence of data generated from various information sources at a high speed and high volume. Classifying data streams faces the three challenges of unlimited length, online processing, and concept drift. In related research, to meet the challenge of unlimited stream length, commonly the stream is divided into fixed size windows or gradual forgetting is used. Concept drift refer...
متن کامل