Journal
PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA
Volume 116, Issue 23, Pages 11537-11546Publisher
NATL ACAD SCIENCES
DOI: 10.1073/pnas.1820226116
Keywords
semantic cognition; deep learning; neural networks; generative models
Categories
Funding
- Burroughs-Wellcome foundation
- Sloan foundation
- McKnight foundation
- James S. McDonnell foundation
- Simons foundation
- Air Force Office of Scientific Research
- Swartz fellowship
- National Defense Science and Engineering Graduate fellowship
- Mind, Brain, & Computation fellowship
Ask authors/readers for more resources
An extensive body of empirical research has revealed remarkable regularities in the acquisition, organization, deployment, and neural representation of human semantic knowledge, thereby raising a fundamental conceptual question: What are the theoretical principles governing the ability of neural networks to acquire, organize, and deploy abstract knowledge by integrating across many individual experiences? We address this question by mathematically analyzing the nonlinear dynamics of learning in deep linear networks. We find exact solutions to this learning dynamics that yield a conceptual explanation for the prevalence of many disparate phenomena in semantic cognition, including the hierarchical differentiation of concepts through rapid developmental transitions, the ubiquity of semantic illusions between such transitions, the emergence of item typicality and category coherence as factors controlling the speed of semantic processing, changing patterns of inductive projection over development, and the conservation of semantic similarity in neural representations across species. Thus, surprisingly, our simple neural model qualitatively recapitulates many diverse regularities underlying semantic development, while providing analytic insight into how the statistical structure of an environment can interact with nonlinear deep-learning dynamics to give rise to these regularities.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available