Artificial Intelligence 293:103438 (2021)

Authors
Jose A. Hernandez
Barry University
Richard Evans
Cambridge University
Abstract
This paper attempts to answer a central question in unsupervised learning: what does it mean to “make sense” of a sensory sequence? In our formalization, making sense involves constructing a symbolic causal theory that both explains the sensory sequence and also satisfies a set of unity conditions. The unity conditions insist that the constituents of the causal theory – objects, properties, and laws – must be integrated into a coherent whole. On our account, making sense of sensory input is a type of program synthesis, but it is unsupervised program synthesis. Our second contribution is a computer implementation, the Apperception Engine, that was designed to satisfy the above requirements. Our system is able to produce interpretable human-readable causal theories from very small amounts of data, because of the strong inductive bias provided by the unity conditions. A causal theory produced by our system is able to predict future sensor readings, as well as retrodict earlier readings, and impute (fill in the blanks of) missing sensory readings, in any combination. In fact, it is able to do all three tasks simultaneously. We tested the engine in a diverse variety of domains, including cellular automata, rhythms and simple nursery tunes, multi-modal binding problems, occlusion tasks, and sequence induction intelligence tests. In each domain, we test our engine's ability to predict future sensor values, retrodict earlier sensor values, and impute missing sensory data. The Apperception Engine performs well in all these domains, significantly out-performing neural net baselines. We note in particular that in the sequence induction intelligence tests, our system achieved human-level performance. This is notable because our system is not a bespoke system designed specifically to solve intelligence tests, but a general-purpose system that was designed to make sense of any sensory sequence.
Keywords unsupervised learning  Kant  structure discovery  program synthesis
Categories (categorize this paper)
DOI 10.1016/j.artint.2020.103438
Options
Edit this record
Mark as duplicate
Export citation
Find it on Scholar
Request removal from index
Revision history

Download options

PhilArchive copy

 PhilArchive page | Other versions
External links

Setup an account with your affiliations in order to access resources via your University's proxy server
Configure custom proxy (use this if your affiliation does not provide a proxy)
Through your library

References found in this work BETA

Core Knowledge.Elizabeth S. Spelke & Katherine D. Kinzler - 2007 - Developmental Science 10 (1):89-96.

View all 10 references / Add more references

Citations of this work BETA

Add more citations

Similar books and articles

Sensory Augmentation and the Tactile Sublime.Yorick Berta - 2020 - Debates in Aesthetics 15 (1):11-33.
Inner-Sense.Vincent Picciuto & Peter Carruthers - forthcoming - In Biggs S., Matthen M. & Stokes D. (eds.), Perception and its Modalites. Oxford University Press.
Enactive Consciousness and Gendlin’s Dream Analysis.R. D. Ellis - 2016 - Constructivist Foundations 11 (2):425-427.
Second Sense: A Theory of Sensory Consciousness.Paula Jean Droege - 2001 - Dissertation, The University of Connecticut
Vision, Vector, Veracity.Tomis Kapitan - 1998 - In Christian Strub (ed.), Blick Und Bild. Wilhelm Fink Verlag.
Making Sense of Phenomenological Sense-Making.David R. Cerbone - 2015 - Philosophical Topics 43 (1-2):253-268.
The Enigma of Perception.D. L. C. Maclachlan - 2013 - Mcgill-Queen's University Press.

Analytics

Added to PP index
2021-01-06

Total views
14 ( #737,966 of 2,533,663 )

Recent downloads (6 months)
5 ( #136,562 of 2,533,663 )

How can I increase my downloads?

Downloads

My notes