Classes of feedforward neural networks and their circuit complexity
نویسندگان
چکیده
منابع مشابه
Classes of feedforward neural networks and their circuit complexity
-Th& paper aims to p&ce neural networks in the conte.\t ol'booh'an citz'ldt complexit.l: 1,1~, de/itte aplm~priate classes qlfeedybrward neural networks with specified fan-in, accm'ac)' olcomputation and depth and ttsing techniques" o./commzmication comph:¥ity proceed to show t/tat the classes.fit into a well-studied hieralz'h)' q/boolean circuits. Results cover both classes of sigmoid activati...
متن کاملPlacing Feedforward Neural Networks Among Several Circuit Complexity Classes
This paper examines the circuit complexity of feedforward neural networks having sigmoid activation function. The starting point is the complexity class NN defined in [18]. First two additional complexity classes NN∆ k and NN∆,ε k having less restrictive conditions (than NN) concerning fan-in and accuracy are defined. We then prove several relations among these three classes and well establishe...
متن کاملCircuit Complexity and Feedforward Neural Networks
Circuit complexity, a subfield of computational complexity theory, can be used to analyze how the resource usage of neural networks scales with problem size. The computational complexity of discrete feedforward neural networks is surveyed, with a comparison of classical circuits to circuits constructed from gates that compute weighted majority functions.
متن کاملthe impact of attending efl classes on the level of depression of iranian female learners and their attributional complexity
می توان گفت واقعیت چند لایه ا ی کلاس های زبان انگلیسی بسیار حائز اهمیت است، زیرا عواطف و بینش های زبان آموزان تحت تاثیر قرار می گیرد. در پژوهش پیش رو، گفته می شود که دبیران با در پیش گرفتن رویکرد فرا-انسانگرایی ، قادرند در زندگی دانش آموزانشان نقش مهمی را ایفا سازند. بر اساس گفته ی ویلیامز و بردن (2000)، برای کرل راجرز، یکی از بنیان گذاران رویکرد انسانگرایی ، یادگیری بر مبنای تجربه، نوعی از یاد...
c - Entropy and the Complexity of Feedforward Neural Networks
We develop a. new feedforward neuralnet.work represent.ation of Lipschitz functions from [0, p]n into [0,1] ba'3ed on the level sets of the function. We show that ~~ + ~€r + ( 1 + h) (:~) n is an upper bound on the number of nodes needed to represent f to within uniform error Cr, where L is the Lipschitz constant. \Ve also show that the number of bits needed to represent the weights in the netw...
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: Neural Networks
سال: 1992
ISSN: 0893-6080
DOI: 10.1016/s0893-6080(05)80093-0