We continue our study from [5], of how concepts that have hierarchical structure might be
represented in brain-like neural networks, how these representations might be used to recognize
the concepts, and how these representations might be learned. In [5], we considered simple
tree-structured concepts and feed-forward layered networks. Here we extend the model in two
ways: we allow limited overlap between children of different concepts, and we allow networks to
include feedback edges. For these more general cases, we describe and analyze algorithms for
recognition and algorithms for learning.
more »
« less
Learning Hierarchically-Structured Concepts II: Overlapping Concepts, and Networks With Feedback
We continue our study from Lynch and Mallmann-Trenn (Neural Networks, 2021), of how concepts that have hierarchical structure might be represented in brain-like neural networks, how these representations might be used to recognize the concepts, and how these representations might be learned. In Lynch and Mallmann-Trenn (Neural Networks, 2021), we considered simple tree-structured concepts and feed-forward layered networks. Here we extend the model in two ways: we allow limited overlap between children of different concepts, and we allow networks to include feedback edges. For these more general cases, we describe and analyze algorithms for recognition and algorithms for learning.
more »
« less
- Award ID(s):
- 1810758
- NSF-PAR ID:
- 10436474
- Date Published:
- Journal Name:
- 30th International Colloquium on Structural Information and Communication Complexity (SIROCCO 2023)
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
null (Ed.)Recent science education reforms, as described in the Framework for K-12 Science Education (NRC, 2012), call for three-dimensional learning that engages students in scientific practices and the use of scientific lenses to learn science content. However, relatively little research at any grade level has focused on how students develop this kind of three-dimensional knowledge that includes crosscutting concepts. This paper aims to contribute to a growing knowledge base that describes how to engage students in three-dimensional learning by exploring to what extent elementary students represent the crosscutting concept systems and system models when engaged in the practice developing and using models as part of an NGSS-aligned curriculum unit. This paper answers the questions: How do students represent elements of crosscutting concepts in conceptual models of water systems? How do students’ representations of crosscutting concepts change related to different task-based scaffolds? To analyze students’ models, we developed and applied a descriptive coding scheme to describe how the students illustrated the flow of water. The results show important differences in how students represented system elements across models. Findings provide insight for the kinds of support that students might need in order to move towards the development of three-dimensional understandings of science content.more » « less
-
null (Ed.)Abstract How does STEM knowledge learned in school change students’ brains? Using fMRI, we presented photographs of real-world structures to engineering students with classroom-based knowledge and hands-on lab experience, examining how their brain activity differentiated them from their “novice” peers not pursuing engineering degrees. A data-driven MVPA and machine-learning approach revealed that neural response patterns of engineering students were convergent with each other and distinct from novices’ when considering physical forces acting on the structures. Furthermore, informational network analysis demonstrated that the distinct neural response patterns of engineering students reflected relevant concept knowledge: learned categories of mechanical structures. Information about mechanical categories was predominantly represented in bilateral anterior ventral occipitotemporal regions. Importantly, mechanical categories were not explicitly referenced in the experiment, nor does visual similarity between stimuli account for mechanical category distinctions. The results demonstrate how learning abstract STEM concepts in the classroom influences neural representations of objects in the world.more » « less
-
more » « less
Abstract Background Biomedical ontologies are representations of biomedical knowledge that provide terms with precisely defined meanings. They play a vital role in facilitating biomedical research in a cross-disciplinary manner. Quality issues of biomedical ontologies will hinder their effective usage. One such quality issue is missing concepts. In this study, we introduce a logical definition-based approach to identify potential missing concepts in SNOMED CT. A unique contribution of our approach is that it is capable of obtaining both logical definitions and fully specified names for potential missing concepts.
Method The logical definitions of unrelated pairs of fully defined concepts in non-lattice subgraphs that indicate quality issues are intersected to generate the logical definitions of potential missing concepts. A text summarization model (called PEGASUS) is fine-tuned to predict the fully specified names of the potential missing concepts from their generated logical definitions. Furthermore, the identified potential missing concepts are validated using external resources including the Unified Medical Language System (UMLS), biomedical literature in PubMed, and a newer version of SNOMED CT.
Results From the March 2021 US Edition of SNOMED CT, we obtained a total of 30,313 unique logical definitions for potential missing concepts through the intersecting process. We fine-tuned a PEGASUS summarization model with 289,169 training instances and tested it on 36,146 instances. The model achieved 72.83 of ROUGE-1, 51.06 of ROUGE-2, and 71.76 of ROUGE-L on the test dataset. The model correctly predicted 11,549 out of 36,146 fully specified names in the test dataset. Applying the fine-tuned model on the 30,313 unique logical definitions, 23,031 total potential missing concepts were identified. Out of these, a total of 2,312 (10.04%) were automatically validated by either of the three resources.
Conclusions The results showed that our logical definition-based approach for identification of potential missing concepts in SNOMED CT is encouraging. Nevertheless, there is still room for improving the performance of naming concepts based on logical definitions.
-
more » « less
Abstract The remarkable successes of convolutional neural networks (CNNs) in modern computer vision are by now well known, and they are increasingly being explored as computational models of the human visual system. In this paper, we ask whether CNNs might also provide a basis for modeling higher‐level cognition, focusing on the core phenomena of similarity and categorization. The most important advance comes from the ability of CNNs to learn high‐dimensional representations of complex naturalistic images, substantially extending the scope of traditional cognitive models that were previously only evaluated with simple artificial stimuli. In all cases, the most successful combinations arise when CNN representations are used with cognitive models that have the capacity to transform them to better fit human behavior. One consequence of these insights is a toolkit for the integration of cognitively motivated constraints back into CNN training paradigms in computer vision and machine learning, and we review cases where this leads to improved performance. A second consequence is a roadmap for how CNNs and cognitive models can be more fully integrated in the future, allowing for flexible end‐to‐end algorithms that can learn representations from data while still retaining the structured behavior characteristic of human cognition.
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- The DOI is not currently available.
