所羅門諾夫的歸納推理理論

所羅門諾夫的歸納推理理論（Solomonoff's theory of inductive inference）是對奧卡姆剃刀敘述的數學化描述。^[1]^[2]^[3]^[4]^[5]該理論指出：在所有能夠完全描述的已觀測的可計算類中，較短的可計算理論在估計下一次觀測結果的概率時具有較大的權重。簡而言之，在幾組可以給出的答案的假設論述中，假設越少的越被大家選擇。引申為「越簡單的越易行」。

參考資料

^ JJ McCall. Induction: From Kolmogorov and Solomonoff to De Finetti and Back to Kolmogorov – Metroeconomica, 2004 – Wiley Online Library.
^ D Stork. Foundations of Occam's razor and parsimony in learning from ricoh.com – NIPS 2001 Workshop, 2001
^ A.N. Soklakov. Occam's razor as a formal basis for a physical theory from arxiv.org – Foundations of Physics Letters, 2002 – Springer
^ Jose Hernandez-Orallo. Beyond the Turing Test (PDF). Journal of Logic, Language and Information. 1999, 9 [2018-07-31]. （原始內容存檔 (PDF)於2018-10-09）.
^ M Hutter. On the existence and convergence of computable universal priors arxiv.org – Algorithmic Learning Theory, 2003 – Springer

[ReferenceA-1] JJ McCall. Induction: From Kolmogorov and Solomonoff to De Finetti and Back to Kolmogorov – Metroeconomica, 2004 – Wiley Online Library.

[ReferenceB-2] D Stork. Foundations of Occam's razor and parsimony in learning from ricoh.com – NIPS 2001 Workshop, 2001

[ReferenceC-3] A.N. Soklakov. Occam's razor as a formal basis for a physical theory from arxiv.org – Foundations of Physics Letters, 2002 – Springer

[Hernandez.1999-4] Jose Hernandez-Orallo. Beyond the Turing Test (PDF). Journal of Logic, Language and Information. 1999, 9 [2018-07-31]. （原始內容存檔 (PDF)於2018-10-09）.

[Hutter.2003-5] M Hutter. On the existence and convergence of computable universal priors arxiv.org – Algorithmic Learning Theory, 2003 – Springer

[1]

[2]

[3]

[4]

[5]