Connectionism

Connectionism (the term itself being coined by Edward Thorndike

in the 1930s) is a name of an approach to the study of human
mental processes with many 'waves'. The first one appeared in the
1950s with Warren Sturgis McCulloch and Walter Pitts both
focusing on comprehending neural circuitry through a formal and
mathematical approach, and Frank Rosenblatt who published the
1958 book “The Perceptron: A Probabilistic Model For Information
Storage and Organization in the Brain” in Psychological Review,
while working at the Cornell Aeronautical Laboratory.[1]

The first wave ended with the 1969 book about the limitations of
the original perceptron idea, written by Marvin Minsky and Papert, A 'second wave' connectionist (ANN)
which contributed to discouraging major funding agencies in the model with a hidden layer
US from investing in connectionist research.[2] With a few
noteworthy deviations, the majority of connectionist research
entered a period of inactivity until the mid-1980s.

The second wave began in the late 1980s, following the 1987 book about Parallel Distributed Processing
by James L. McClelland, David E. Rumelhart et al., which introduced a couple of improvements to the
simple perceptron idea, such as intermediate processors (known as "hidden layers" now) alongside input
and output units and used sigmoid activation function instead of the old 'all-or-nothing' function. Their
work has, in turn, built upon that of John Hopfield, who was a key figure investigating the mathematical
characteristics of sigmoid activation functions.[1] From the late 1980s to the mid-1990s, connectionism took
on an almost revolutionary tone when Schneider,[3] Terence Horgan and Tienson posed the question of
whether connectionism represented a fundamental shift in psychology and GOFAI.[1] Some advantages of
the second wave connectionist approach included its applicability to a broad array of functions, structural
approximation to biological neurons, low requirements for innate structure, and capacity for graceful
degradation.[4] Some disadvantages of the second wave connectionist approach included the difficulty in
deciphering how ANNs process information, or account for the compositionality of mental representations,
and a resultant difficulty explaining phenomena at a higher level.[5]

The current (third) wave has been marked by advances in Deep Learning allowing for Large language
models.[1] The success of deep learning networks in the past decade has greatly increased the popularity of
this approach, but the complexity and scale of such networks has brought with them increased
interpretability problems.[6]

Basic principle
The central connectionist principle is that mental phenomena can be described by interconnected networks
of simple and often uniform units. The form of the connections and the units can vary from model to model.
For example, units in the network could represent neurons and the connections could represent synapses, as
in the human brain. This principle has been seen as an alternative to GOFAI and the classical theories of
mind based on symbolic computation, but the extent to which the two approaches are compatible has been
the subject of much debate since their inception.[6]

Activation function

Internal states of any network change over time due to neurons sending a signal to a succeeding layer of
neurons in the case of a feedforward network, or to a previous layer in the case of a recurrent network.
Discovery of non-linear activation functions has enabled the second wave of connectionism.

Memory and learning

Neural networks follow two basic principles:

1. Any mental state can be described as an (N)-dimensional vector of numeric activation

values over neural units in a network.
2. Memory and learning are created by modifying the 'weights' of the connections between
neural units, generally represented as an N×M matrix. The weights are adjusted according
to some learning rule or algorithm, such as Hebbian learning.[7]

Most of the variety among the models comes from:

Interpretation of units: Units can be interpreted as neurons or groups of neurons.

Definition of activation: Activation can be defined in a variety of ways. For example, in a
Boltzmann machine, the activation is interpreted as the probability of generating an action
potential spike, and is determined via a logistic function on the sum of the inputs to a unit.
Learning algorithm: Different networks modify their connections differently. In general, any
mathematically defined change in connection weights over time is referred to as the
"learning algorithm".

Biological realism

Connectionist work in general does not need to be biologically realistic.[8][9][10][11][12][13][14] One area
where connectionist models are thought to be biologically implausible is with respect to error-propagation
networks that are needed to support learning,[15][16] but error propagation can explain some of the
biologically-generated electrical activity seen at the scalp in event-related potentials such as the N400 and
P600,[17] and this provides some biological support for one of the key assumptions of connectionist
learning procedures. Many recurrent connectionist models also incorporate dynamical systems theory.
Many researchers, such as the connectionist Paul Smolensky, have argued that connectionist models will
evolve toward fully continuous, high-dimensional, non-linear, dynamic systems approaches.

Precursors
Precursors of the connectionist principles can be traced to early work in psychology, such as that of William
James.[18] Psychological theories based on knowledge about the human brain were fashionable in the late
19th century. As early as 1869, the neurologist John Hughlings Jackson argued for multi-level, distributed
systems. Following from this lead, Herbert Spencer's Principles of Psychology, 3rd edition (1872), and
Sigmund Freud's Project for a Scientific Psychology (composed 1895) propounded connectionist or proto-
connectionist theories. These tended to be speculative theories. But by the early 20th century, Edward
Thorndike was experimenting on learning that posited a connectionist type network.

Friedrich Hayek independently conceived the Hebbian synapse learning model in a paper presented in
1920 and developed that model into global brain theory constituted of networks Hebbian synapses building
into larger systems of maps and memory network. Hayek's breakthrough work was cited by Frank
Rosenblatt in his perceptron paper.

The first wave

The first wave begun in 1950s with Warren Sturgis McCulloch and Walter Pitts both focusing on
comprehending neural circuitry through a formal and mathematical approach, and Frank Rosenblatt who
published the 1958 book “The Perceptron: A Probabilistic Model For Information Storage and
Organization in the Brain” in Psychological Review, while working at the Cornell Aeronautical
Laboratory.[1] McCulloch and Pitts showed how neural systems could implement first-order logic: Their
classic paper "A Logical Calculus of Ideas Immanent in Nervous Activity" (1943) is important in this
development here. They were influenced by the important work of Nicolas Rashevsky in the 1930s. Hebb
contributed greatly to speculations about neural functioning, and proposed a learning principle, Hebbian
learning, that is still used today. Lashley argued for distributed representations as a result of his failure to
find anything like a localized engram in years of lesion experiments. Another form of connectionist model
was the relational network framework developed by the linguist Sydney Lamb in the 1960s.

The second wave

The second wave begun in late 1980s, following the 1987 book about the Parallel Distributed Processing
by James L. McClelland, David E. Rumelhart et al., which has introduced a couple of improvements to the
simple perceptron idea, such as intermediate processors (known as "hidden layers" now) alongside input
and output units and using sigmoid activation function instead of the old 'all-or-nothing' function. Their
work has, in turn, built upon John Hopfield, who was a key figure investigating the mathematical
characteristics of sigmoid activation functions.[1] A lot of the research that led to the development of PDP
was done in the 1970s, although the term "connectionism" was not used. The first deep learning MLP was
published by Alexey Grigorevich Ivakhnenko and Valentin Lapa in 1965 in USSS (Ukrainian Soviet
Socialist Republic), as the Group Method of Data Handling.[19][20][21] This method employs incremental
layer by layer training based on regression analysis, where useless units in hidden layers are pruned with
the help of a validation set. The history of recurrent neural networks (RNNs) goes back even further to the
1920s. Wilhelm Lenz (1920) and Ernst Ising (1925) created and analyzed the Ising model[22] which is
essentially a non-learning RNN consisting of neuron-like threshold elements.[19] In 1972, Shun'ichi Amari
made this architecture adaptive.[23][19] The first deep learning MLP trained by stochastic gradient
descent[24] was published in 1967 by Shun'ichi Amari.[25][19] In computer experiments conducted by
Amari's student Saito, a five layer MLP with two modifiable layers learned useful internal representations to
classify non-linearily separable pattern classes.[19]

Connectionism vs. computationalism debate

As connectionism became increasingly popular in the late 1980s, some researchers (including Jerry Fodor,
Steven Pinker and others) reacted against it. They argued that connectionism, as then developing,
threatened to obliterate what they saw as the progress being made in the fields of cognitive science and
psychology by the classical approach of computationalism. Computationalism is a specific form of
cognitivism that argues that mental activity is computational, that is, that the mind operates by performing
purely formal operations on symbols, like a Turing machine. Some researchers argued that the trend in
connectionism represented a reversion toward associationism and the abandonment of the idea of a
language of thought, something they saw as mistaken. In contrast, those very tendencies made
connectionism attractive for other researchers.

Connectionism and computationalism need not be at odds, but the debate in the late 1980s and early 1990s
led to opposition between the two approaches. Throughout the debate, some researchers have argued that
connectionism and computationalism are fully compatible, though full consensus on this issue has not been
reached. Differences between the two approaches include the following:

Computationalists posit symbolic models that are structurally similar to underlying brain
structure, whereas connectionists engage in "low-level" modeling, trying to ensure that their
models resemble neurological structures.
Computationalists in general focus on the structure of explicit symbols (mental models) and
syntactical rules for their internal manipulation, whereas connectionists focus on learning
from environmental stimuli and storing this information in a form of connections between
neurons.
Computationalists believe that internal mental activity consists of manipulation of explicit
symbols, whereas connectionists believe that the manipulation of explicit symbols provides
a poor model of mental activity.
Computationalists often posit domain specific symbolic sub-systems designed to support
learning in specific areas of cognition (e.g., language, intentionality, number), whereas
connectionists posit one or a small set of very general learning-mechanisms.

Despite these differences, some theorists have proposed that the connectionist architecture is simply the
manner in which organic brains happen to implement the symbol-manipulation system. This is logically
possible, as it is well known that connectionist models can implement symbol-manipulation systems of the
kind used in computationalist models,[26] as indeed they must be able if they are to explain the human
ability to perform symbol-manipulation tasks. Several cognitive models combining both symbol-
manipulative and connectionist architectures have been proposed. Among them are Paul Smolensky's
Integrated Connectionist/Symbolic Cognitive Architecture (ICS).[6][27] and Ron Sun's CLARION
(cognitive architecture). But the debate rests on whether this symbol manipulation forms the foundation of
cognition in general, so this is not a potential vindication of computationalism. Nonetheless, computational
descriptions may be helpful high-level descriptions of cognition of logic, for example.

The debate was largely centred on logical arguments about whether connectionist networks could produce
the syntactic structure observed in this sort of reasoning. This was later achieved although using fast-
variable binding abilities outside of those standardly assumed in connectionist models.[26][28]

Part of the appeal of computational descriptions is that they are relatively easy to interpret, and thus may be
seen as contributing to our understanding of particular mental processes, whereas connectionist models are
in general more opaque, to the extent that they may be describable only in very general terms (such as
specifying the learning algorithm, the number of units, etc.), or in unhelpfully low-level terms. In this sense,
connectionist models may instantiate, and thereby provide evidence for, a broad theory of cognition (i.e.,
connectionism), without representing a helpful theory of the particular process that is being modelled. In
this sense, the debate might be considered as to some extent reflecting a mere difference in the level of
analysis in which particular theories are framed. Some researchers suggest that the analysis gap is the
consequence of connectionist mechanisms giving rise to emergent phenomena that may be describable in
computational terms.[29]
In the 2000s, the popularity of dynamical systems in philosophy of mind have added a new perspective on
the debate;[30][31] some authors now argue that any split between connectionism and computationalism is
more conclusively characterized as a split between computationalism and dynamical systems.

In 2014, Alex Graves and others from DeepMind published a series of papers describing a novel Deep
Neural Network structure called the Neural Turing Machine[32] able to read symbols on a tape and store
symbols in memory. Relational Networks, another Deep Network module published by DeepMind, are
able to create object-like representations and manipulate them to answer complex questions. Relational
Networks and Neural Turing Machines are further evidence that connectionism and computationalism need
not be at odds.

Symbolism vs. connectionism debate

Smolensky's Subsymbolic Paradigm[33][34] has to meet the Fodor-Pylyshyn challenge[35][36][37][38]
formulated by classical symbol theory for a convincing theory of cognition in modern connectionism. In
order to be an adequate alternative theory of cognition, Smolensky's Subsymbolic Paradigm would have to
explain the existence of systematicity or systematic relations in language cognition without the assumption
that cognitive processes are causally sensitive to the classical constituent structure of mental representations.
The subsymbolic paradigm, or connectionism in general, would thus have to explain the existence of
systematicity and compositionality without relying on the mere implementation of a classical cognitive
architecture. This challenge implies a dilemma: If the Subsymbolic Paradigm could contribute nothing to
the systematicity and compositionality of mental representations, it would be insufficient as a basis for an
alternative theory of cognition. However, if the Subsymbolic Paradigm's contribution to systematicity
requires mental processes grounded in the classical constituent structure of mental representations, the
theory of cognition it develops would be, at best, an implementation architecture of the classical model of
symbol theory and thus not a genuine alternative (connectionist) theory of cognition.[39] The classical
model of symbolism is characterized by (1) a combinatorial syntax and semantics of mental representations
and (2) mental operations as structure-sensitive processes, based on the fundamental principle of syntactic
and semantic constituent structure of mental representations as used in Fodor's "Language of Thought
(LOT)".[40][41] This can be used to explain the following closely related properties of human cognition,
namely its (1) productivity, (2) systematicity, (3) compositionality, and (4) inferential coherence.[42]

This challenge has been met in modern connectionism, for example, not only by Smolensky's "Integrated
Connectionist/Symbolic (ICS) Cognitive Architecture",[43][44] but also by Werning and Maye's
"Oscillatory Networks".[45][46][47] An overview of this is given for example by Bechtel & Abrahamsen,[48]
Marcus[49] and Maurer.[50]

See also
Associationism Eliminative materialism
Artificial intelligence Feature integration theory
Behaviorism Genetic algorithm
Catastrophic interference Harmonic grammar
Calculus of relations Machine learning
Cybernetics Pandemonium architecture
Deep learning Self-organizing map

Notes
 1. Berkeley, Istvan S. N. (2019). "The Curious Case of Connectionism" (https://www.degruyter.c
om/document/doi/10.1515/opphil-2019-0018/html). Open Philosophy. 2019 (2): 190–205.
2. Boden, Margaret (2006). Mind as Machine: A History of Cognitive Science (https://archive.or
g/details/mindasmachinehis0002bode/page/n5/mode/thumb). Oxford: Oxford U.P. p. 914.
ISBN 978-0-262-63268-3.
3. Schneider, Walter (1987). "Connectionism: Is it a Paradigm Shift for Psychology?" (https://w
ww.degruyter.com/document/doi/10.1515/opphil-2019-0018/html). Behavior Research
Methods, Instruments & Computers. 19: 73–83.
4. Marcus, Gary F. (2001). The Algebraic Mind: Integrating Connectionism and Cognitive
Science (Learning, Development, and Conceptual Change) (https://archive.org/details/algeb
raicmindint00marc_403). Cambridge, Massachusetts: MIT Press. pp. 27 (https://archive.org/
details/algebraicmindint00marc_403/page/n43)–28. ISBN 978-0-262-63268-3.
5. Smolensky, Paul (1999). "Grammar-based Connectionist Approaches to Language" (https://
doi.org/10.1207%2Fs15516709cog2304_9). Cognitive Science. 23 (4): 589–613.
doi:10.1207/s15516709cog2304_9 (https://doi.org/10.1207%2Fs15516709cog2304_9).
6. Garson, James (27 November 2018). Zalta, Edward N. (ed.). The Stanford Encyclopedia of
Philosophy (https://plato.stanford.edu/archives/fall2018/entries/connectionism/).
Metaphysics Research Lab, Stanford University – via Stanford Encyclopedia of Philosophy.
7. Novo, María-Luisa; Alsina, Ángel; Marbán, José-María; Berciano, Ainhoa (2017).
"Connective Intelligence for Childhood Mathematics Education" (https://doi.org/10.3916%2F
c52-2017-03). Comunicar (in Spanish). 25 (52): 29–39. doi:10.3916/c52-2017-03 (https://doi.
org/10.3916%2Fc52-2017-03). ISSN 1134-3478 (https://www.worldcat.org/issn/1134-3478).
8. "Encephalos Journal" (http://www.encephalos.gr/48-1-01e.htm). www.encephalos.gr.
Retrieved 2018-02-20.
9. Wilson, Elizabeth A. (2016-02-04). Neural Geographies: Feminism and the Microstructure of
Cognition (https://books.google.com/books?id=s-OCCwAAQBAJ&q=%22accurate%22&pg=
PT18). Routledge. ISBN 978-1-317-95876-5.
10. "Organismically-inspired robotics: homeostatic adaptation and teleology beyond the closed
sensorimotor loop" (https://www.semanticscholar.org/paper/Organismically-inspired-robotics
-%3A-homeostatic-and-Paolo/d9827462bcf6b8e55e7c28897c293c3c92ba34d8). Semantic
Scholar. S2CID 15349751 (https://api.semanticscholar.org/CorpusID:15349751).
11. Zorzi, Marco; Testolin, Alberto; Stoianov, Ivilin P. (2013-08-20). "Modeling language and
cognition with deep unsupervised learning: a tutorial overview" (https://www.ncbi.nlm.nih.go
v/pmc/articles/PMC3747356). Frontiers in Psychology. 4: 515.
doi:10.3389/fpsyg.2013.00515 (https://doi.org/10.3389%2Ffpsyg.2013.00515). ISSN 1664-
1078 (https://www.worldcat.org/issn/1664-1078). PMC 3747356 (https://www.ncbi.nlm.nih.go
v/pmc/articles/PMC3747356). PMID 23970869 (https://pubmed.ncbi.nlm.nih.gov/23970869).
12. "ANALYTIC AND CONTINENTAL PHILOSOPHY" (http://scholarworks.sjsu.edu/cgi/viewcon
tent.cgi?article=1015&context=comparativephilosophy).
13. Browne, A. (1997-01-01). Neural Network Perspectives on Cognition and Adaptive Robotics
(https://books.google.com/books?id=uV9TZzOITMwC&q=%22biological%20plausibility%22
&pg=PA17). CRC Press. ISBN 978-0-7503-0455-9.
14. Pfeifer, R.; Schreter, Z.; Fogelman-Soulié, F.; Steels, L. (1989-08-23). Connectionism in
Perspective (https://books.google.com/books?id=7pPv0STSos8C&q=%22biological+realis
m%22&pg=PA63). Elsevier. ISBN 978-0-444-59876-9.
15. Crick, Francis (January 1989). "The recent excitement about neural networks". Nature. 337
(6203): 129–132. Bibcode:1989Natur.337..129C (https://ui.adsabs.harvard.edu/abs/1989Nat
ur.337..129C). doi:10.1038/337129a0 (https://doi.org/10.1038%2F337129a0). ISSN 1476-
4687 (https://www.worldcat.org/issn/1476-4687). PMID 2911347 (https://pubmed.ncbi.nlm.ni
h.gov/2911347). S2CID 5892527 (https://api.semanticscholar.org/CorpusID:5892527).
16. Rumelhart, David E.; Hinton, Geoffrey E.; Williams, Ronald J. (October 1986). "Learning
representations by back-propagating errors". Nature. 323 (6088): 533–536.
Bibcode:1986Natur.323..533R (https://ui.adsabs.harvard.edu/abs/1986Natur.323..533R).
doi:10.1038/323533a0 (https://doi.org/10.1038%2F323533a0). ISSN 1476-4687 (https://ww
w.worldcat.org/issn/1476-4687). S2CID 205001834 (https://api.semanticscholar.org/CorpusI
D:205001834).
17. Fitz, Hartmut; Chang, Franklin (2019-06-01). "Language ERPs reflect learning through
prediction error propagation". Cognitive Psychology. 111: 15–52.
doi:10.1016/j.cogpsych.2019.03.002 (https://doi.org/10.1016%2Fj.cogpsych.2019.03.002).
hdl:21.11116/0000-0003-474F-6 (https://hdl.handle.net/21.11116%2F0000-0003-474F-6).
ISSN 0010-0285 (https://www.worldcat.org/issn/0010-0285). PMID 30921626 (https://pubme
d.ncbi.nlm.nih.gov/30921626). S2CID 85501792 (https://api.semanticscholar.org/CorpusID:8
5501792).
18. Anderson, James A.; Rosenfeld, Edward (1989). "Chapter 1: (1890) William James
Psychology (Brief Course)". Neurocomputing: Foundations of Research. A Bradford Book.
p. 1. ISBN 978-0-262-51048-6.
19. Schmidhuber, Juergen (2022). "Annotated History of Modern AI and Deep Learning".
arXiv:2212.11279 (https://arxiv.org/abs/2212.11279) [cs.NE (https://arxiv.org/archive/cs.NE)].
20. Ivakhnenko, A. G. (1973). Cybernetic Predicting Devices (https://books.google.com/books?id
=FhwVNQAACAAJ). CCM Information Corporation.
21. Ivakhnenko, A. G.; Grigorʹevich Lapa, Valentin (1967). Cybernetics and forecasting
techniques (https://books.google.com/books?id=rGFgAAAAMAAJ). American Elsevier Pub.
Co.
22. Brush, Stephen G. (1967). "History of the Lenz-Ising Model". Reviews of Modern Physics. 39
(4): 883–893. Bibcode:1967RvMP...39..883B (https://ui.adsabs.harvard.edu/abs/1967RvM
P...39..883B). doi:10.1103/RevModPhys.39.883 (https://doi.org/10.1103%2FRevModPhys.3
9.883).
23. Amari, Shun-Ichi (1972). "Learning patterns and pattern sequences by self-organizing nets
of threshold elements". IEEE Transactions. C (21): 1197–1206.
24. Robbins, H.; Monro, S. (1951). "A Stochastic Approximation Method" (https://doi.org/10.121
4%2Faoms%2F1177729586). The Annals of Mathematical Statistics. 22 (3): 400.
doi:10.1214/aoms/1177729586 (https://doi.org/10.1214%2Faoms%2F1177729586).
25. Amari, Shun'ichi (1967). "A theory of adaptive pattern classifier". IEEE Transactions. EC
(16): 279–307.
26. Chang, Franklin (2002). "Symbolically speaking: a connectionist model of sentence
production" (https://doi.org/10.1207%2Fs15516709cog2605_3). Cognitive Science. 26 (5):
609–651. doi:10.1207/s15516709cog2605_3 (https://doi.org/10.1207%2Fs15516709cog260
5_3). ISSN 1551-6709 (https://www.worldcat.org/issn/1551-6709).
27. Smolensky, Paul (1990). "Tensor Product Variable Binding and the Representation of
Symbolic Structures in Connectionist Systems" (http://www.lscp.net/persons/dupoux/teachin
g/AT1_2012/papers/Smolensky_1990_TensorProductVariableBinding.AI.pdf) (PDF).
Artificial Intelligence. 46 (1–2): 159–216. doi:10.1016/0004-3702(90)90007-M (https://doi.or
g/10.1016%2F0004-3702%2890%2990007-M).
28. Shastri, Lokendra; Ajjanagadde, Venkat (September 1993). "From simple associations to
systematic reasoning: A connectionist representation of rules, variables and dynamic
bindings using temporal synchrony". Behavioral and Brain Sciences. 16 (3): 417–451.
doi:10.1017/S0140525X00030910 (https://doi.org/10.1017%2FS0140525X00030910).
ISSN 1469-1825 (https://www.worldcat.org/issn/1469-1825). S2CID 14973656 (https://api.se
manticscholar.org/CorpusID:14973656).
29. Ellis, Nick C. (1998). "Emergentism, Connectionism and Language Learning" (http://www-pe
rsonal.umich.edu/~ncellis/NickEllis/Publications_files/Emergentism.pdf) (PDF). Language
Learning. 48:4 (4): 631–664. doi:10.1111/0023-8333.00063 (https://doi.org/10.1111%2F002
3-8333.00063).
30. Van Gelder, Tim (1998), "The dynamical hypothesis in cognitive science" (https://www.cambr
idge.org/core/services/aop-cambridge-core/content/view/S0140525X98271731), Behavioral
and Brain Sciences, 21 (5): 615–28, discussion 629-65, doi:10.1017/S0140525X98001733
(https://doi.org/10.1017%2FS0140525X98001733), PMID 10097022 (https://pubmed.ncbi.nl
m.nih.gov/10097022), retrieved 28 May 2022
31. Beer, Randall D. (March 2000). "Dynamical approaches to cognitive science". Trends in
Cognitive Sciences. 4 (3): 91–99. doi:10.1016/s1364-6613(99)01440-0 (https://doi.org/10.10
16%2Fs1364-6613%2899%2901440-0). ISSN 1364-6613 (https://www.worldcat.org/issn/13
64-6613). PMID 10689343 (https://pubmed.ncbi.nlm.nih.gov/10689343). S2CID 16515284
(https://api.semanticscholar.org/CorpusID:16515284).
32. Graves, Alex (2014). "Neural Turing Machines". arXiv:1410.5401 (https://arxiv.org/abs/1410.
5401) [cs.NE (https://arxiv.org/archive/cs.NE)].
33. P. Smolensky: On the proper treatment of connectionism. In: Behavioral and Brain Sciences.
Band 11, 1988, S. 1-74.
34. P. Smolensky: The constituent structure of connectionist mental states: a reply to Fodor and
Pylyshyn. In: T. Horgan, J. Tienson (Hrsg.): Spindel Conference 1987: Connectionism and
the Philosophy of Mind. The Southern Journal of Philosophy. Special Issue on
Connectionism and the Foundations of Cognitive Science. Supplement. Band 26, 1988, S.
137-161.
35. J.A. Fodor, Z.W. Pylyshyn: Connectionism and cognitive architecture: a critical analysis.
Cognition. Band 28, 1988, S. 12-13, 33-50.
36. J.A. Fodor, B. McLaughlin: Connectionism and the problem of systematicity: why
Smolensky's solution doesn't work. Cognition. Band 35, 1990, S. 183-184.
37. B. McLaughlin: The connectionism/classicism battle to win souls. Philosophical Studies,
Band 71, 1993, S. 171-172.
38. B. McLaughlin: Can an ICS architecture meet the systematicity and productivity challenges?
In: P. Calvo, J. Symons (Hrsg.): The Architecture of Cognition. Rethinking Fodor and
Pylyshyn's Systematicity Challenge. MIT Press, Cambridge/MA, London, 2014, S. 31-76.
39. J.A. Fodor, B. McLaughlin: Connectionism and the problem of systematicity: Why
Smolensky's solution doesn't work. Cognition. Band 35, 1990, S. 183-184.
40. J.A. Fodor: The language of thought. Harvester Press, Sussex, 1976, ISBN 0-85527-309-7.
41. J.A. Fodor: LOT 2: The language of thought revisited. Clarendon Press, Oxford, 2008, ISBN
0-19-954877-3.
42. J.A. Fodor, Z.W. Pylyshyn (1988), S. 33-48.
43. P. Smolenky: Reply: Constituent structure and explanation in an integrated connectionist /
symbolic cognitive architecture. In: C. MacDonald, G. MacDonald (Hrsg.): Connectionism:
Debates on psychological explanation. Blackwell Publishers. Oxford/UK, Cambridge/MA.
Vol. 2, 1995, S. 224, 236-239, 242-244, 250-252, 282.
44. P. Smolensky, G. Legendre: The Harmonic Mind: From Neural Computation to Optimality-
Theoretic Grammar. Vol. 1: Cognitive Architecture. A Bradford Book, The MIT Press,
Cambridge, London, 2006a, ISBN 0-262-19526-7, S. 65-67, 69-71, 74-75, 154-155, 159-
202, 209-210, 235-267, 271-342, 513.
45. M. Werning: Neuronal synchronization, covariation, and compositional representation. In: M.
Werning, E. Machery, G. Schurz (Hrsg.): The compositionality of meaning and content. Vol.
II: Applications to linguistics, psychology and neuroscience. Ontos Verlag, 2005, S. 283-312.
46. M. Werning: Non-symbolic compositional representation and its neuronal foundation:
towards an emulative semantics. In: M. Werning, W. Hinzen, E. Machery (Hrsg.): The Oxford
Handbook of Compositionality. Oxford University Press, 2012, S. 633-654.
47. A. Maye und M. Werning: Neuronal synchronization: from dynamics feature binding to
compositional representations. Chaos and Complexity Letters, Band 2, S. 315-325.
48. Bechtel,W., Abrahamsen, A.A. Connectionism and the Mind: Parallel Processing, Dynamics,
and Evolution in Networks. 2nd Edition. Blackwell Publishers, Oxford. 2002
49. G.F. Marcus: The algebraic mind. Integrating connectionism and cognitive science. Bradford
Book, The MIT Press, Cambridge, 2001, ISBN 0-262-13379-2.
50. H. Maurer: Cognitive science: Integrative synchronization mechanisms in cognitive
neuroarchitectures of the modern connectionism. CRC Press, Boca Raton/FL, 2021, ISBN
978-1-351-04352-6. https://doi.org/10.1201/9781351043526

References
Rumelhart, D.E., J.L. McClelland and the PDP Research Group (1986). Parallel Distributed
Processing: Explorations in the Microstructure of Cognition. Volume 1: Foundations,
Cambridge, Massachusetts: MIT Press, ISBN 978-0-262-68053-0
McClelland, J.L., D.E. Rumelhart and the PDP Research Group (1986). Parallel Distributed
Processing: Explorations in the Microstructure of Cognition. Volume 2: Psychological and
Biological Models, Cambridge, Massachusetts: MIT Press, ISBN 978-0-262-63110-5
Pinker, Steven and Mehler, Jacques (1988). Connections and Symbols, Cambridge MA: MIT
Press, ISBN 978-0-262-66064-8
Jeffrey L. Elman, Elizabeth A. Bates, Mark H. Johnson, Annette Karmiloff-Smith, Domenico
Parisi, Kim Plunkett (1996). Rethinking Innateness: A connectionist perspective on
development, Cambridge MA: MIT Press, ISBN 978-0-262-55030-7
Marcus, Gary F. (2001). The Algebraic Mind: Integrating Connectionism and Cognitive
Science (Learning, Development, and Conceptual Change), Cambridge, Massachusetts:
MIT Press, ISBN 978-0-262-63268-3
David A. Medler (1998). "A Brief History of Connectionism" (http://www.blutner.de/NeuralNet
s/Texts/Medler.pdf) (PDF). Neural Computing Surveys. 1: 61–101.
Maurer, Harald (2021). Cognitive Science: Integrative Synchronization Mechanisms in
Cognitive Neuroarchitectures of the Modern Connectionism, Boca Raton/FL: CRC Press,
https://doi.org/10.1201/9781351043526, ISBN 978-1-351-04352-6

External links
Dictionary of Philosophy of Mind entry on connectionism (http://philosophy.uwaterloo.ca/Min
dDict/connectionism.html)
Garson, James. "Connectionism" (https://plato.stanford.edu/entries/connectionism/). In Zalta,
Edward N. (ed.). Stanford Encyclopedia of Philosophy.
A demonstration of Interactive Activation and Competition Networks (http://srsc.ulb.ac.be/pd
p/iac/IAC.html)
"Connectionism" (http://www.iep.utm.edu/connect). Internet Encyclopedia of Philosophy.
Critique of connectionism (https://sapienlabs.org/the-crisis-of-computational-neuroscience/)

Retrieved from "https://en.wikipedia.org/w/index.php?title=Connectionism&oldid=1164557329"