more historical perspective on connectionism

I am digging into this topic because I started looking into related topics
and could not see clearly through the literature.  Neuro symbolic
approaches are not new, and there are tons o excellent papers over forty
years old
Richard Lea pointed to another earlier paper,
Neurosymbolic Integration: Cognitive Grounds and Computational Strategies
https://www.academia.edu/27984998/Neurosymbolic_Integration_Cognitive_Grounds_and_Computational_Strategies

<https://independent.academia.edu/YLallement?swp=tc-au-27984998>
in there seminal references including J Hendler
He had a vision o combining connectionism and KR before anyone else, but i
someone ind an even earlier source, please share it
https://www.sciencedirect.com/science/article/abs/pii/0364021389900128
Marker-passing over microfeatures: towards hybrid symbolic/connectionist
model☆
<https://www.sciencedirect.com/science/article/abs/pii/0364021389900128#aep-article-footnote-id1>
Author links open overlay panelJames A.Hendler
<https://www.sciencedirect.com/science/article/abs/pii/0364021389900128#!>
https://doi.org/10.1016/0364-0213(89)90012-8Get rights and content
<https://s100.copyright.com/AppDispatchServlet?publisherName=ELS&contentID=0364021389900128&orderBeanReset=true>
Abstract

Spreading activation, in the form of computer models and cognitive
theories, has recently been undergoing a resurgence of interest in the
cognitive science and AI communities. Two different types of cognitive
models have been proposed to explain the activation spreading results. One
approach, that of *marker-passing*, concentrates on the spreading of
symbolic information through an associative knowledge representation. The
other technique, including the work in *local connectionism*, has focused
on the passage of numeric information through a network. In this article,
it is shown that these two techniques can be merged. The implementation of
a mechanism in which a local-connectionist-like model is integrated with a
symbolic marker-passer is described and shows that the combined system is
more powerful than either of the separate models alone. Finally, some early
steps toward a hybrid model in which a distributed network is used to learn
the microfeatures is described.

<https://www.avast.com/sig-email?utm_medium=email&utm_source=link&utm_campaign=sig-email&utm_content=webmail&utm_term=icon>
Virus-free.
www.avast.com
<https://www.avast.com/sig-email?utm_medium=email&utm_source=link&utm_campaign=sig-email&utm_content=webmail&utm_term=link>
<#DAB4FAD8-2DD7-40BB-A1B8-4E2AA1F9FDF2>