A distributed connectionist representation for concept structures

نویسندگان

  • David S. Touretzky
  • Shai Geva
  • S. Geva
چکیده

We describe a representation for frame-like concept structures in a neural network called DUCS. Slot names and slot fillers are diffuse patterns of activation spread over a collection of units. Our choice of a distributed representation gives rise to certain useful properties not shared by conventional frame systems. One of these is the ability to encode fine semantic distinctions as subtle variations on the canonical pattern for a slot. DUCS typically maintains several concepts simultaneously in its concept memory; it can retrieve a concept given one or more slots as cues. We show how Hinton's notion of a "reduced description" can be used to make one concept fill a slot in another.

برای دانلود رایگان 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

Compositional connectionist structures based on in situ grounded representations

The combination of productivity, dynamics and grounding imposes constraints that require specific architectures for their combined implementation. Grounding of representations can be achieved with specific neuronal assembly structures, which can be distributed over different brain areas. This entails that grounded conceptual representations cannot be copied, transported and pasted to form compo...

متن کامل

Holistic Computation: Reconstructing a Muddled Concept

It has been claimed that connectionist methods of encoding compositional structures, such as Pollack's RAAM, support a non-classical form of structure sensitive operation known as holistic computation, where symbol structures can be acted upon holistically without the need to decompose them, or to perform a search to locate or access their constituents. In this paper, it is argued that the conc...

متن کامل

Evaluation of Two Connectionist Approaches to Stack Representation

This study empirically compares two distributed connectionist learning models trained to represent an arbitrarily deep stack. One is Pol-lack's Recursive Auto-Associative Memory, a recurrent back propagating neural network that uses a hidden intermediate representation. The other is the Exponential Decay Model, a novel architecture that we propose here, which tries to learn an explicit represen...

متن کامل

Distributed Connectionist Models in Social Psychology

Distributed connectionist models of mental representation (also termed PDP or parallel distributed processing, or ANN or artificial neural networks) constitute a fundamental alternative to the associative or schematic models that have been much more prevalent in social psychology. A connectionist model is made up of a large number of very simple processing units, richly interconnected and able ...

متن کامل

Evaluation of Two Connectionist Approaches toStack

This study empirically compares two distributed connectionist learning models trained to represent an arbitrarily deep stack. One is Pol-lack's Recursive Auto-Associative Memory, a recurrent back propagating neural network that uses a hidden intermediate representation. The other is the Exponential Decay Model, a novel architecture that we propose here, which tries to learn an explicit represen...

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

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2015