Philip Huebner

Philip Huebner
University of Illinois, Urbana-Champaign | UIUC · Department of Psychology

BSc

About

9
Publications
1,587
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
177
Citations
Introduction
Philip Huebner studies computational models of language acquisition, and in particular RNN and Transformer-based language models.
Skills and Expertise
Additional affiliations
September 2014 - present
University of California, Riverside
Position
  • PhD Student
January 2012 - January 2014
University of California, Davis
Position
  • Undergraduate Research Asssistant
September 2010 - September 2014
University of California, Davis
Position
  • Research Assistant

Publications

Publications (9)
Article
Full-text available
Previous research has suggested that distributional learning mechanisms may contribute to the acquisition of semantic knowledge. However, distributional learning mechanisms, statistical learning, and contemporary “deep learning” approaches have been criticized for being incapable of learning the kind of abstract and structured knowledge that many t...
Conference Paper
Full-text available
Some researchers claim that language acquisition is critically dependent on experiencing linguistic input in order of increasing complexity. We set out to test this hypothesis using a simple recurrent neural network (SRN) trained to predict word sequences in CHILDES, a 5-million-word corpus of speech directed to children. First, we demonstrated tha...
Chapter
Full-text available
Prior work has demonstrated that distributional dependencies between word or morpheme-like entities in artificial and naturalistic language can detect clusters of words which broadly conform to the categories of the adult language (Brent & Siskind, 2001; Mintz, 2002; Redington & Chater, 1998). In this work, we examine the hypothesis that the distri...
Article
We followed a patient with manganese transporter deficiency due to homozygous SLC30A10 mutations from age 14 years until his death at age 38 years and present the first postmortem findings of this disorder. The basal ganglia showed neuronal loss, rhodanine-positive deposits, astrocytosis, myelin loss and spongiosis. SLC30A10 protein was reduced in...
Article
Full-text available
Importance: Magnetic resonance imaging markers of incipient cognitive decline among healthy elderly individuals have become important for both clarifying the biological underpinnings of dementia and clinically identifying healthy individuals at high risk of cognitive decline. Even though the role of hippocampal atrophy is well known in the later s...

Network

Cited By

Projects

Projects (2)
Archived project
Project
What can we learn from modeling concept acquisition in recurrent neural networks?