Fodor and Pylyshyn argued that connectionist models could not be used to exhibit and explain a phenomenon that they termed systematicity, i.e., compositional syntax and semantics for mental representations and structure sensitivity of mental processes. This inability, they argued, was particularly serious since it meant that connectionist models could not be used as alternative models to classical symbolic models to explain cognition. In this paper, a connectionist model is used to identify some properties which show that connectionist networks supply means for accomplishing a stronger version of systematicity than Fodor and Pylyshyn opted for. Specifically, it is argued that context-dependent systematicity is achievable within a connectionist framework. The arguments put forward rest on a particular formulation of content and context of connectionist representation, firmly and technically based on connectionist primitives in a learning environment. The perspective is motivated by the fundamental differences between the connectionist and classical architectures, in terms of prerequisites, lower-level functionality and inherent constraints. 2
|
1177
|
A logic for default reasoning
– Reiter
- 1979
|
|
1092
|
Finding structure in time
– Elman
- 1990
|
|
524
|
A framework for representing knowledge
– Minsky
|
|
401
|
Parallel networks that learn to pronounce english text
– Sejnowski, Rosenberg
- 1987
|
|
394
|
Connectionism and cognitive architecture: A critical analysis
– Fodor, Pylyshyn
- 1988
|
|
308
|
Recursive distributed representations
– Pollack
- 1990
|
|
295
|
A learning algorithm for Boltzmann Machines
– Ackley, Hinton, et al.
- 1985
|
|
243
|
Semantic Memory
– Quillian
- 1968
|
|
185
|
Tensor product variable binding and the representation of symbolic structures in connectionist systems
– Smolensky
- 1990
|
|
177
|
Distributed representations
– Hinton, McClelland, et al.
- 1986
|
|
113
|
Syntactic transformations on distributed representations
– Chalmers
- 1990
|
|
108
|
A clash of intuitions: The current state of nonmonotonic multiple inheritance systems
– Touretzky, Horty, et al.
- 1987
|
|
85
|
Compositionality: A connectionist variation on a classical theme
– Gelder
- 1990
|
|
76
|
Fundamental aspects of cognitive representation
– Palmer
- 1978
|
|
72
|
Learning internal representations by back propagation
– Rumelhart, Hinton, et al.
- 1986
|
|
60
|
Learning recursive distributed representations for holistic computation
– Chrisman
- 1991
|
|
53
|
Connectionism and the problem of systematicity: Why Smolensky’s solution doesn’t work
– Fodor, McLaughlin
- 1990
|
|
38
|
What connectionist models learn: Learning and representation in connectionist networks
– Hanson, Burr
- 1990
|
|
37
|
Systematicity in connectionist language learning. Mind and Language
– Hadley
- 1994
|
|
37
|
Nonmonotonic Inference Rules for Multiple Inheritance with Exceptions. in: Proceedin s of the
– Sandewall
- 1975
|
|
32
|
The Mathematics of Inheritance
– Touretzky
- 1986
|
|
24
|
Connectionist representation techniques
– Sharkey
- 1991
|
|
24
|
The constituent structure of connectionist mental states: a reply to Fodor and Pylyshyn
– Smolensky
- 1987
|
|
23
|
Associative Engines
– Clark
- 1993
|
|
23
|
An internal report for connectionists
– Sharkey, Jackson
- 1994
|
|
17
|
Strong systematicity within connectionism -- the tensor-recurrent network
– Phillips
- 1994
|
|
16
|
Subsymbolic computation and the chinese room
– Chalmers
- 1992
|
|
16
|
Structure sensitivity in connectionist models
– Niklasson
- 1993
|
|
15
|
Exploring the symbolic /subsymbolic continuum: A case study of RAAM
– Blank, Meeden, et al.
- 1992
|
|
15
|
Strong semantic systematicity from Hebbian connectionist learning
– Hadley, Hayward
- 1997
|
|
14
|
Features of distributed representations for treestructures: A study of RAAM
– Bod'en, Niklasson
- 1995
|
|
14
|
Classical Questions, Radical Answers: Connectionism and the Structure of Mental Representations
– Gelder
- 1991
|
|
13
|
What is the `D' in `PDP'? A survey of the concept of distribution
– Gelder
- 1991
|
|
12
|
The Concept of Representation and the Representation of Concepts in Connectionist Models
– Goschke, Koppelberg
- 1991
|
|
11
|
Representing structure and structured representations in connectionist networks
– Niklasson, Bodén
- 1997
|
|
11
|
Connectionism and the issues of compositionality and systematicity
– Niklasson, Sharkey
- 1992
|
|
10
|
On being systematically connectionist. Mind and Language
– Niklasson, Gelder
- 1994
|
|
8
|
Classicalism and cognitive architecture
– Gelder, Niklasson
- 1994
|
|
6
|
A connectionist variation on inheritance
– Bod'en
- 1996
|
|
5
|
Context-sensitive Connectionist Representations for Nonmonotonic Inheritance
– Bod'en
- 1997
|
|
5
|
Systematicity revisited: Reply to Chater & Christiansen and Niklasson
– Hadley
- 1994
|
|
5
|
Systematicity, the Scarlet Pimpernel of Cognitive Science
– Niklasson
- 1995
|
|
4
|
Connectionism and constituent structure
– Smolensky
- 1989
|
|
