How deeply does Sutskever's List cover inductive inference?

Defines the problem and illustrates two philosophical constraints, then motivates weighted consideration of computable programs without deriving a formal method.

Inductive inference

As explained in Sutskever's List

Inductive inference is the process of inferring the process or hypothesis that could have generated observed data.

Inductive inference asks how an observer can infer the process that produced observed data. In Legg’s framing, it supplies foundations for an idealized agent intended to go beyond systems limited to specific tasks. section 9.1.2

Two principles constrain how hypotheses are considered:

Epicurus’s principle of multiple explanations says not to discard hypotheses that fit the evidence. Missing cookies and a moved chair could implicate either a child or a burglar. section 9.1.2
Occam’s razor favors the simplest hypothesis consistent with the evidence. For 1, 3, 5, 7…, 9 is preferred over a more complicated prediction such as 33. section 9.1.2

Together, these principles motivate considering all computable programs, weighted appropriately, rather than relying on a single task-specific explanation. section 9.1.2

How Sutskever's List covers it

liveBook manning.com

Read Sutskever's List on liveBook Get the book at manning.com

Also explained in

liveBook manning.com

Knowledge Graphs and LLMs in ActionInductive reasoning is the derivation of general patterns, conclusions, or predictions from observed cases, including cases with incomplete information.
liveBook manning.com

Graph Neural Networks in ActionInductive learning learns a generalizable function or representation from observed data for application to unseen data.

Compare how 3 books explain inductive inference →

Related concepts

transductive learningcontrasts with · Transductive learning infers representations or predictions for specific entities and structures observed during training rather than learning rules that generalize to unseen entities.
generalizationproduces · Generalization is the extension of a pattern, model, solution, or conclusion beyond the specific examples or cases from which it was derived.
multi-step reasoningkind of · Multi-step reasoning derives a conclusion, solution, or decision through multiple connected intermediate inferential or problem-solving steps.
deductive reasoningcontrasts with · Deductive reasoning is the process of deriving conclusions that necessarily follow from stated general premises, rules, or hypotheses.
machine learninguses · Machine learning is a field of computational methods in which systems learn patterns or relationships from data to make predictions, decisions, or other outputs.

This explainer was generated by Manning's knowledge graph from the text of Sutskever's List. The section links point to the parts of the book it draws on.