翻訳と辞書 |
Hutter Prize : ウィキペディア英語版 | Hutter Prize
The Hutter Prize is a cash prize funded by Marcus Hutter which rewards data compression improvements on a specific 100 MB English text file. Specifically, the prize awards 500 euros for each one percent improvement (with 50,000 euros total funding)〔Marcus Hutter, Human Knowledge Compression Contest, http://prize.hutter1.net/〕 in the compressed size of the file ''enwik8'', which is the smaller of two files used in the (Large Text Compression Benchmark ); enwik8 is the first 100,000,000 characters of a specific version of English Wikipedia.〔Matt Mahoney, About the Test Data http://mattmahoney.net/dc/textdata.html〕 The ongoing competition is organized by Hutter, Matt Mahoney, and Jim Bowery. ==Goals== The goal of the Hutter Prize is to encourage research in artificial intelligence (AI). The organizers believe that text compression and AI are equivalent problems. Hutter proved〔Marcus Hutter, Universal Artificial Intelligence: Sequential Decisions based on Algorithmic Probability, Springer, Berlin, 2004, http://www.hutter1.net/ai/uaibook.htm〕 that the optimal behavior of a goal seeking agent in an unknown but computable environment is to guess at each step that the environment is probably controlled by one of the shortest programs consistent with all interaction so far. Unfortunately, there is no general solution because Kolmogorov complexity is not computable. Hutter proved that in the restricted case (called AIXItl) where the environment is restricted to time ''t'' and space ''l'', that a solution can be computed in time ''O''(t2l), which is still intractable. The organizers further believe that compressing natural language text is a hard AI problem, equivalent to passing the Turing test. Thus, progress toward one goal represents progress toward the other.〔Matt Mahoney, Rationale for a Large Text Compression Benchmark, 2006, http://mattmahoney.net/dc/rationale.html〕 They argue that predicting which characters are most likely to occur next in a text sequence requires vast real-world knowledge. A text compressor must solve the same problem in order to assign the shortest codes to the most likely text sequences.
抄文引用元・出典: フリー百科事典『 ウィキペディア(Wikipedia)』 ■ウィキペディアで「Hutter Prize」の詳細全文を読む
スポンサード リンク
翻訳と辞書 : 翻訳のためのインターネットリソース |
Copyright(C) kotoba.ne.jp 1997-2016. All Rights Reserved.
|
|