Preprint

In recent years, deep artificial neural networks (including recurrent ones) have won numerous contests in pattern recognition and machine learning. This historical survey compactly summarises relevant work, much of it from the previous millennium. Shallow and deep learners are distinguished by the depth of their credit assignment paths, which are chains of possibly learnable, causal links between actions and effects. It reviews deep supervised learning (also recapitulating the history of backpropagation), unsupervised learning, reinforcement learning & evolutionary computation, and indirect search for short programs encoding deep and large networks.

Contributed by close colleagues, friends, and former students of Floris Takens, Global Analysis of Dynamical Systems is a liber amicorum dedicated to Takens for his 60th birthday.

Многое в истории нашего отечества, да и всего мира, нуждается в уточнениях и корректировке. Это признают и сами историки. Однако уточненная история, как правило, не всегда становится достоянием широкой читательской аудитории. Большинству из нас тайны нашего прошлого никогда не раскроются. Одна из причин заключается в том, что историки намеренно искажают нашу историю.

This book is the first volume of a two-volume work, which is an improved version of a preprint [47] published in German. We seek to deduce the funda­ mental concepts of quantum mechanics solely from a description of macroscopic devices. The microscopic systems such as electrons, atoms, etc. must be detected on the basis of the macroscopic behavior of the devices. This detection resembles the detection of the dinosaurs on the basis offossils. In this first volume we develop a general description of macroscopic systems by trajectories in state spaces.

This book is the first volume of a two-volume work, which is an improved version of a preprint published in German. We seek to deduce the funda­ mental concepts of quantum mechanics solely from a description of macroscopic devices. The microscopic systems such as electrons, atoms, etc. must be detected on the basis of the macroscopic behavior of the devices.