Abstract category learning

نویسندگان

  • Atsushi Hashimoto
  • Haruo Hosoya
چکیده

Category Learning Atsushi Hashimoto and Haruo Hosoya Department of Computer Science The University of Tokyo 7-3-1 Hongo, Bunkyo-ku, Tokyo, Japan Abstract. Motivated by a neurophysiological experiment on prefrontal cortex, we study a scheme for learning abstract categories. An abstract category represents a set of vectors that are identical to each other modulo substitution, e.g., ’ABAB’, ’BABA’, ’ACAC’, etc. We employ a clusteringbased unsupervised learning method for such abstract categories, in which the recognition step is reduced to the problem of maximal perfect weight matching. Our simulations using artificial inputs confirm that the scheme learns abstract categories robustly even with a certain level of noise in the inputs. Motivated by a neurophysiological experiment on prefrontal cortex, we study a scheme for learning abstract categories. An abstract category represents a set of vectors that are identical to each other modulo substitution, e.g., ’ABAB’, ’BABA’, ’ACAC’, etc. We employ a clusteringbased unsupervised learning method for such abstract categories, in which the recognition step is reduced to the problem of maximal perfect weight matching. Our simulations using artificial inputs confirm that the scheme learns abstract categories robustly even with a certain level of noise in the inputs.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Learning Abstract Relations Through Analogy to Concrete Exemplars

We present a model that bridges work in analogy and category learning. The model, Building Relations through Instance Driven Gradient Error Shifting (BRIDGES), extends ALCOVE, an exemplar-based connectionist model of category learning (Kruschke, 1992). Unlike ALCOVE which is limited to featural or spatial representations, BRIDGES can appreciate analogical relationships between stimuli and store...

متن کامل

The multifaceted nature of unsupervised category learning.

A substantial portion of category-learning research has focused on one learning mode--namely, classification learning (a supervised learning mode). Subsequently, theories of category learning have focused on how the abstract structure of categories (i.e., the co-occurrence patterns of feature values) affects acquisition. Recent work in supervised learning has shown that a learner's interactions...

متن کامل

CALF: Categorical Automata Learning Framework

Automata learning is a technique that has successfully been applied in verification, with the automaton type varying depending on the application domain. Adaptations of automata learning algorithms for increasingly complex types of automata have to be developed from scratch because there was no abstract theory offering guidelines. This makes it hard to devise such algorithms, and it obscures th...

متن کامل

Twenty - First Annual Conference of the Cognitive Science Society

In this paper, we compare the rhetoric that sometimes appears in the literature on computational models of category learning with the growing evidence that different theoretical paradigms typically produce similar results. In response, we suggest that concrete computational models, which currently dominate the eld, may be less useful than simulations that operate at a more abstract level. We il...

متن کامل

Category Discontinuity Interacts with Verbal Rule Complexity 1 Within-Category Discontinuity Interacts with Verbal Rule Complexity in Perceptual Category Learning

Two experiments were conducted that provide a test of the predicted interaction between within-category discontinuity and verbal rule complexity on the efficiency of the neurobiologically-motivated procedural-based and hypothesis-testing category learning systems, and by extension, on information-integration and rule-based category learning. In Experiment 1, within-category discontinuity advers...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2011