Kolmogorov’s Theorem: From Algebraic Equations and Nomography to Neural Networks
We trace the developments around Hilbert’s thirteenth problem back to questions concerning algebraic equations.
Its solution, namely Kolmogorov’s superposition theorem of 1956, is stated in an elaborate form and its relation with neural nets is explained. A detailed proof allows to initiate discussions concerning implementability.
We address individuals interested to form an opinion about the hotly debated applicability of the superposition theorem but also the philosophically inclined readers that want to learn the background of a mathematical problem with an eventful history, and who, by studying its proof will get a sense of the difference between construction and existence in mathematics.
KeywordsBaire Category Theorem Elaborate Form Superposition Theorem Alignment Chart Index Triple
Unable to display preview. Download preview PDF.
- Burnside W S and Panton A W, ‘The Theory of Equations’, Reprint of the seventh edition of 1912, Dover 1960.Google Scholar
- Levens A S, ‘Nomography’, John Wiley, New York, 1959.Google Scholar
- ‘Andreij Nikolajevic Kolmogorov’, Obituary. Bull. London. Math. Soc. 22, 1, 37–68, 1990.Google Scholar
- Boas R P, ‘A Primer of Real Functions’, third edition, Carus Mathematical Monograph 13, The Mathematical Association of America, 1981.Google Scholar