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

  1. ^ JJ McCall. Induction: From Kolmogorov and Solomonoff to De Finetti and Back to Kolmogorov – Metroeconomica, 2004 – Wiley Online Library.
  2. ^ D Stork. Foundations of Occam's razor and parsimony in learning from ricoh.com – NIPS 2001 Workshop, 2001
  3. ^ A.N. Soklakov. Occam's razor as a formal basis for a physical theory from arxiv.org – Foundations of Physics Letters, 2002 – Springer
  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). 
  5. ^ M Hutter. On the existence and convergence of computable universal priors arxiv.org – Algorithmic Learning Theory, 2003 – Springer