The "Explanation Hypothesis" in General Self-Supervised Learning

Kristinn R. Thórisson
Proceedings of the Second International Workshop on Self-Supervised Learning, PMLR 159:5-27, 2022.

Abstract

Self-supervised learning is the ability of an agent to improve its own performance, with respect to one or more goals related to one or more phenomena, without outside help from a teacher or other external aid tailored to the agent’s learning progress. A general learner’s learning process is not limited to a strict set of topics, tasks, or domains. Selfsupervised and general learning machines are still in the early stages of development, as are learning machines that can explain their own knowledge, goals, actions, and reasoning. Research on explanation proper has to date been largely limited to the field of philosophy of science. In this paper I present the hypothesis that general self-supervised learning requires (a particular kind of) explanation generation, and review some key arguments for and against it. Named the explanation hypothesis (ExH), the claim rests on three main pillars. First, that any good explanation of a phenomenon requires reference to relations between sub-parts of that phenomenon, as well as to its context (other phenomena and their parts), especially (but not only) causal relations. Second, that self-supervised general learning of a new phenomenon requires (a kind of) bootstrapping, and that this - and subsequent improvement on the initial knowledge thus produced - relies on reasoning processes. Third, that general self-supervised learning relies on reification of prior knowledge and knowledge-generation processes, which can only be implemented through appropriate reflection mechanisms, whereby current knowledge and prior learning progress is available for explicit inspection by the learning system itself, to be analyzed for use in future learning. The claim thus construed has several important implications for the implementation of general machine intelligence, including that it will neither be achieved without reflection (meta-cognition) nor explicit representation of causal relations, and that internal explanation generation must be a fundamental principle of their operation.

Cite this Paper

BibTeX
@InProceedings{pmlr-v159-thorisson22b, title = {The "Explanation Hypothesis" in General Self-Supervised Learning}, author = {Th\'orisson, Kristinn R.}, booktitle = {Proceedings of the Second International Workshop on Self-Supervised Learning}, pages = {5--27}, year = {2022}, editor = {Thórisson, Kristinn R. and Robertson, Paul}, volume = {159}, series = {Proceedings of Machine Learning Research}, month = {13--14 Aug}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v159/thorisson22b/thorisson22b.pdf}, url = {https://proceedings.mlr.press/v159/thorisson22b.html}, abstract = {Self-supervised learning is the ability of an agent to improve its own performance, with respect to one or more goals related to one or more phenomena, without outside help from a teacher or other external aid tailored to the agent’s learning progress. A general learner’s learning process is not limited to a strict set of topics, tasks, or domains. Selfsupervised and general learning machines are still in the early stages of development, as are learning machines that can explain their own knowledge, goals, actions, and reasoning. Research on explanation proper has to date been largely limited to the field of philosophy of science. In this paper I present the hypothesis that general self-supervised learning requires (a particular kind of) explanation generation, and review some key arguments for and against it. Named the explanation hypothesis (ExH), the claim rests on three main pillars. First, that any good explanation of a phenomenon requires reference to relations between sub-parts of that phenomenon, as well as to its context (other phenomena and their parts), especially (but not only) causal relations. Second, that self-supervised general learning of a new phenomenon requires (a kind of) bootstrapping, and that this - and subsequent improvement on the initial knowledge thus produced - relies on reasoning processes. Third, that general self-supervised learning relies on reification of prior knowledge and knowledge-generation processes, which can only be implemented through appropriate reflection mechanisms, whereby current knowledge and prior learning progress is available for explicit inspection by the learning system itself, to be analyzed for use in future learning. The claim thus construed has several important implications for the implementation of general machine intelligence, including that it will neither be achieved without reflection (meta-cognition) nor explicit representation of causal relations, and that internal explanation generation must be a fundamental principle of their operation.} }
Endnote
%0 Conference Paper %T The "Explanation Hypothesis" in General Self-Supervised Learning %A Kristinn R. Thórisson %B Proceedings of the Second International Workshop on Self-Supervised Learning %C Proceedings of Machine Learning Research %D 2022 %E Kristinn R. Thórisson %E Paul Robertson %F pmlr-v159-thorisson22b %I PMLR %P 5--27 %U https://proceedings.mlr.press/v159/thorisson22b.html %V 159 %X Self-supervised learning is the ability of an agent to improve its own performance, with respect to one or more goals related to one or more phenomena, without outside help from a teacher or other external aid tailored to the agent’s learning progress. A general learner’s learning process is not limited to a strict set of topics, tasks, or domains. Selfsupervised and general learning machines are still in the early stages of development, as are learning machines that can explain their own knowledge, goals, actions, and reasoning. Research on explanation proper has to date been largely limited to the field of philosophy of science. In this paper I present the hypothesis that general self-supervised learning requires (a particular kind of) explanation generation, and review some key arguments for and against it. Named the explanation hypothesis (ExH), the claim rests on three main pillars. First, that any good explanation of a phenomenon requires reference to relations between sub-parts of that phenomenon, as well as to its context (other phenomena and their parts), especially (but not only) causal relations. Second, that self-supervised general learning of a new phenomenon requires (a kind of) bootstrapping, and that this - and subsequent improvement on the initial knowledge thus produced - relies on reasoning processes. Third, that general self-supervised learning relies on reification of prior knowledge and knowledge-generation processes, which can only be implemented through appropriate reflection mechanisms, whereby current knowledge and prior learning progress is available for explicit inspection by the learning system itself, to be analyzed for use in future learning. The claim thus construed has several important implications for the implementation of general machine intelligence, including that it will neither be achieved without reflection (meta-cognition) nor explicit representation of causal relations, and that internal explanation generation must be a fundamental principle of their operation.
APA
Thórisson, K.R.. (2022). The "Explanation Hypothesis" in General Self-Supervised Learning. Proceedings of the Second International Workshop on Self-Supervised Learning, in Proceedings of Machine Learning Research 159:5-27 Available from https://proceedings.mlr.press/v159/thorisson22b.html.

Related Material