Boolean Function Complexity and Neural Networks
نویسندگان
چکیده
A new neural network (NN) approach is proposed in this paper to estimate the Boolean function (BF) complexity. Large number of randomly generated single output BFs has been used and experimental results show good correlation between the theoretical results and those predicted by the NN model. The proposed model is capable of predicting the number of product terms (NPT) in the BF that gives an indication on its complexity.
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 کاملDecomposition of Boolean Function Sets for Boolean Neural Networks
This paper presents a new type of neuron, called Boolean neuron. We suggest algorithms for decomposition of Boolean functions sets based on Boolean neural networks that include only Boolean neurons. The advantages of these neural networks consist in the reduction of memory space and computation time in comparison to the representation of Boolean functions by usual neural networks. The Boolean n...
متن کاملExtracting Propositions from Trained Neural Networks
This paper presents an algorithm for extract ing propositions from trained neural networks. The algorithm is a decompositional approach which can be applied to any neural network whose output function is monotone such as sig moid function. Therefore, the algorithm can be applied to multi-layer neural networks, re current neural networks and so on. The algorithm does not depend on training me...
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 کاملAn Attractor-Based Complexity Measurement for Boolean Recurrent Neural Networks
We provide a novel refined attractor-based complexity measurement for Boolean recurrent neural networks that represents an assessment of their computational power in terms of the significance of their attractor dynamics. This complexity measurement is achieved by first proving a computational equivalence between Boolean recurrent neural networks and some specific class of ω-automata, and then t...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2006