It is well-known that abstract neurons of the McCulloch-Pitts type com-pute input-output functions that are formally equivalent to suitably defined Boolean functions. Boolean functions, in turn, can be classified (up to iso-morphism of underlying logical structure) into a limited number of basic types, each of which is non-isomorphic to each other type. These basic types are conveniently expressed by means of a canonic logical formula involving a minimal number of constituent operations. Each such canonic formula can be translated into an equivalent representation as a neural circuit, re-sulting in a catalog of basic, distinct neural circuits. Each circuit in this catalog computes a distinct Boolean function, and every Boolean function is c...
The most commonly used neural network models are not well suited to direct digital implementations b...
In this talk, I present a formal model of biological neural networks and discuss the use of model ch...
A hypothesis is proposed that multiple LOGIC genes control Boolean logic in a neuron. Each hypothe...
This report surveys some connections between Boolean functions and artificial neural networks. The f...
This report surveys some connections between Boolean functions and artificial neural networks. The f...
This paper presents a new type of neuron, called Boolean neuron. We suggest algorithms for decomposi...
This paper deals with the representation of Boolean functions using artificial neural networks and p...
This paper aims to place neural networks in the context of boolean circuit complexity. We define app...
The concept of a “Neural Code " is based on the assumption that the brain performs computations...
The use of Boolean models I n the study of biological networks was proposed and worked out already i...
The magnitude and apparent complexity of the brain's connectivity have left explicit networks largel...
A new conceptual framework and a minimization principle together provide an understanding of computa...
<p>The circuit diagrams show that neurons with excitatory and inhibitory inputs and neurons that hav...
The aim of this book is to describe the types of computation that can be performed by biologically p...
We show that neural networks with three-times continuously differentiable activation functions are c...
The most commonly used neural network models are not well suited to direct digital implementations b...
In this talk, I present a formal model of biological neural networks and discuss the use of model ch...
A hypothesis is proposed that multiple LOGIC genes control Boolean logic in a neuron. Each hypothe...
This report surveys some connections between Boolean functions and artificial neural networks. The f...
This report surveys some connections between Boolean functions and artificial neural networks. The f...
This paper presents a new type of neuron, called Boolean neuron. We suggest algorithms for decomposi...
This paper deals with the representation of Boolean functions using artificial neural networks and p...
This paper aims to place neural networks in the context of boolean circuit complexity. We define app...
The concept of a “Neural Code " is based on the assumption that the brain performs computations...
The use of Boolean models I n the study of biological networks was proposed and worked out already i...
The magnitude and apparent complexity of the brain's connectivity have left explicit networks largel...
A new conceptual framework and a minimization principle together provide an understanding of computa...
<p>The circuit diagrams show that neurons with excitatory and inhibitory inputs and neurons that hav...
The aim of this book is to describe the types of computation that can be performed by biologically p...
We show that neural networks with three-times continuously differentiable activation functions are c...
The most commonly used neural network models are not well suited to direct digital implementations b...
In this talk, I present a formal model of biological neural networks and discuss the use of model ch...
A hypothesis is proposed that multiple LOGIC genes control Boolean logic in a neuron. Each hypothe...