The expressive power of analog recurrent neural networks on infinite input streams
نویسندگان
چکیده
منابع مشابه
The expressive power of analog recurrent neural networks on infinite input streams
We consider analog recurrent neural networks working on infinite input streams, provide a complete topological characterization of their expressive power, and compare it to the expressive power of classical infinite word reading abstract machines. More precisely, we consider analog recurrent neural networks as language recognizers over the Cantor space, and prove that the classes of ω-languages...
متن کاملExpressive power of recurrent neural networks
Deep neural networks are surprisingly efficient at solving practical tasks, but the theory behind this phenomenon is only starting to catch up with the practice. Numerous works show that depth is the key to this efficiency. A certain class of deep convolutional networks – namely those that correspond to the Hierarchical Tucker (HT) tensor decomposition – has been proven to have exponentially hi...
متن کاملOn the Expressive Power of Joint Input
The join-calculus was introduced as anèxtended subset' of the asynchronous-calculus by amalgamating the three operators for input, restriction, and replication into a single operator, called deenition, but with the additional capability to describe the atomic joint reception of values from two diierent channels. In this paper, we just extend the asynchronous-calculus with joint input. By studyi...
متن کاملOn the Expressive Power of Deep Neural Networks
We propose a new approach to the problem of neural network expressivity, which seeks to characterize how structural properties of a neural network family affect the functions it is able to compute. Our approach is based on an interrelated set of measures of expressivity, unified by the novel notion of trajectory length, which measures how the output of a network changes as the input sweeps alon...
متن کاملInput output stability of recurrent neural networks
i Foreword Recurrent neural networks are an attractive tool for both practical applications and for the modeling of biological nerve nets, but their successful application requires an understanding of their dynamical properties, in particular, their stability. The present work provides an in-depth study of this challenging issue and contributes a number of new results that are also important fo...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Theoretical Computer Science
سال: 2012
ISSN: 0304-3975
DOI: 10.1016/j.tcs.2012.01.042