Titlebook: Neural Networks and Analog Computation; Beyond the Turing Li Hava T. Siegelmann Book 1999 Birkh?user Boston 1999 Natur.Theorie.complexity.c

commotion

書(shū)目名稱(chēng)Neural Networks and Analog Computation影響因子(影響力)




書(shū)目名稱(chēng)Neural Networks and Analog Computation影響因子(影響力)學(xué)科排名




書(shū)目名稱(chēng)Neural Networks and Analog Computation網(wǎng)絡(luò)公開(kāi)度




書(shū)目名稱(chēng)Neural Networks and Analog Computation網(wǎng)絡(luò)公開(kāi)度學(xué)科排名




書(shū)目名稱(chēng)Neural Networks and Analog Computation被引頻次




書(shū)目名稱(chēng)Neural Networks and Analog Computation被引頻次學(xué)科排名




書(shū)目名稱(chēng)Neural Networks and Analog Computation年度引用




書(shū)目名稱(chēng)Neural Networks and Analog Computation年度引用學(xué)科排名




書(shū)目名稱(chēng)Neural Networks and Analog Computation讀者反饋




書(shū)目名稱(chēng)Neural Networks and Analog Computation讀者反饋學(xué)科排名

INERT

小口啜飲

Universality of Sigmoidal Networks,dal-like” activation functions, suggesting that Turing universality is a common property of recurrent neural network models. In conclusion, the computational capabilities of sigmoidal networks are located in between Turing machines and advice Turing machines.

Bone-Scan

Allege

詞根詞綴法

Kolmogorov Weights: Between P and P/poly,recursive functions. This chapter proves the intuitive notion that as the real numbers used grow richer in information, more functions become computable. To formalize this statement, we need a measure by which to quantify the information contained in real numbers.

Exclude

Stochastic Dynamics,ty in networks, e.g., [vN56, Pip90, Adl78, Pip88, Pip89, DO77a, DO77b], studied only acyclic architectures of binary gates, while we study general architectures of analog components. Due to these two qualitative differences, our results are totally different from the previous ones, and require new proof techniques.

無(wú)關(guān)緊要

Computational Complexity,computational models. Our presentation starts with elementary definitions of computational theory, but gradually builds to advanced topics; each computational term introduced is immediately related to neural models.

Epidural-Space

Networks with Rational Weights, values only, here a neuron can take on countably infinite different values. The analysis of networks with rational weights is a prerequisite for the proofs of the real weight model in the next chapter. It also sheds light on the role of different types of weights in determining the computational capabilities of the model.

anagen

Different-limits Networks,er is much wider than that of the previous chapter, and as a result the lower bound on its computational power is weaker. We prove that any function for which the left and right limits exist and are different can serve as an activation function for the neurons to yield a network that is at least as strong computationally as a finite automaton.