Results 1  10
of
10
Some epistemological implications of devices which construct their own sensors and effectors
 Proceedings of the First European Conference on Artificial Life
, 1992
"... 493. Formatting and pagination have been changed from the original. Various classes of physical devices having adaptive sensors, coordinative parts, and/or effectors are considered with respect to the kinds of informational relations they permit the device to have with its environment. Devices which ..."
Abstract

Cited by 28 (4 self)
 Add to MetaCart
(Show Context)
493. Formatting and pagination have been changed from the original. Various classes of physical devices having adaptive sensors, coordinative parts, and/or effectors are considered with respect to the kinds of informational relations they permit the device to have with its environment. Devices which can evolve their own physical hardware can expand their repertoires of measurements, computations, and controls in a manner analogous to the structural evolution of sensory, coordinative, and effector organs over phylogeny. In particular, those devices which have the capacity to adaptively construct new sensors and effectors gain the ability to modify the relationship between their internal states and the world at large. Such devices in effect adaptively create their own (semantic) categories rather than having them explicitly specified by an external designer. An electrochemical device built in the 1950's which evolved the capacity to sense sound is discussed as a rudimentary exemplar of a class of adaptive, sensorevolving devices. Such devices could potentially serve as semanticallyadaptive frontends for computationallyadaptive classifiers, by altering the feature primitives (primitive categories) that the classifier operates with. Networks composed of elements capable of evolving new sensors and
On computation with pulses
 Information and Computation
, 1999
"... We explore the computational power of formal models for computation with pulses. Such models are motivated by realistic models for biological neurons, and by related new types of VLSI (\pulse stream VLSI"). In preceding work it was shown that the computational power of formal models for com ..."
Abstract

Cited by 15 (1 self)
 Add to MetaCart
We explore the computational power of formal models for computation with pulses. Such models are motivated by realistic models for biological neurons, and by related new types of VLSI (\pulse stream VLSI&quot;). In preceding work it was shown that the computational power of formal models for computation with pulses is quite high if the pulses arriving at a computational unit have an approximately linearly rising or linearly decreasing initial segment. This property is satis ed by common models for biological neurons. On the other hand several implementations of pulse stream VLSI employ pulses that are approximately piecewise constant (i.e. step functions). In this article we investigate the relevance of the shape of pulses in formal models for computation with pulses. It turns out that the computational power drops signi cantly if one replaces pulses with linearly rising or decreasing initial segments by piecewise constant pulses. We provide an exact characterization of the latter model in terms of a weak version of a random access machine (RAM). We also compare the language recognition capability of a recurrent version of this model with that of deterministic nite automata and Turing machines. 1
On the Relevance of the Shape of Postsynaptic Potentials for the Computational Power of Spiking Neurons
 Proc. of the International Conference on Artificial Neural Networks (ICANN
, 1995
"... The firing of a neuron in a biological neural system causes in certain other neurons excitatory postsynaptic potential changes (EPSP's) that are not "rectangular", but have the form of a smooth hill. We prove in this article for a formal model of a network of spiking neurons, that the ..."
Abstract

Cited by 9 (8 self)
 Add to MetaCart
(Show Context)
The firing of a neuron in a biological neural system causes in certain other neurons excitatory postsynaptic potential changes (EPSP's) that are not "rectangular", but have the form of a smooth hill. We prove in this article for a formal model of a network of spiking neurons, that the rising respectively declining segments of these EPSP's are in fact essential for the computational power of the model. 1 Introduction Apparently all computations in biological neural systems are realized through sequences of firings of neurons as a result of incoming postsynaptic potentials, see e.g. (Kandel et al., 1991). Each firing of a neuron in a biological neural system causes excitatory or inhibitory postsynaptic potentials (EPSP's respectively IPSP's) in those other neurons to which it is connected by synapses. A neuron fires if the sum of its incoming postsynaptic potentials becomes larger than its current threshold (which depends on the time of its last previous firing) . Recently one has also ...
The Computational Power of Spiking Neurons Depends on the Shape of the Postsynaptic Potentials
, 1996
"... Recently one has started to investigate the computational power of spiking neurons (also called "integrate and fire neurons"). These are neuron models that are substantially more realistic from the biological point of view than the ones which are traditionally employed in artificial neu ..."
Abstract

Cited by 4 (0 self)
 Add to MetaCart
Recently one has started to investigate the computational power of spiking neurons (also called "integrate and fire neurons"). These are neuron models that are substantially more realistic from the biological point of view than the ones which are traditionally employed in artificial neural nets. It has turned out that the computational power of networks of spiking neurons is quite large. In particular they have the ability to communicate and manipulate analog variables in spatiotemporal coding, i.e. encoded in the time points when specific neurons "fire" (and thus send a "spike" to other neurons). These preceding results have motivated the question which details of the firing mechanism of spiking neurons are essential for their computational power, and which details are "accidental" aspects of their realization in biological "wetware". Obviously this question becomes important if one wants to capture some of the advantages of computing and learning with spatiotemporal c...
Information and Computation 148, 202218 (1999) On Computation with Pulses
"... We explore the computational power of formal models for computation with pulses. Such models are motivated by realistic models for biological neurons and by related new types of VLSI (‘‘pulse stream VLSI’’). In preceding work it was shown that the computational power of formal models for computation ..."
Abstract
 Add to MetaCart
We explore the computational power of formal models for computation with pulses. Such models are motivated by realistic models for biological neurons and by related new types of VLSI (‘‘pulse stream VLSI’’). In preceding work it was shown that the computational power of formal models for computation with pulses is quite high if the pulses arriving at a computational unit have an approximately linearly rising or linearly decreasing initial segment. This property is satisfied by common models for biological neurons. On the other hand, several implementations of pulse stream VLSI employ pulses that are approximately piecewise constant (i.e., step functions). In this article we investigate the relevance of the shape of pulses in formal models for computation with pulses. The results show that the computational power drops significantly if one replaces pulses with linearly rising or decreasing initial segments by piecewise constant pulses. We provide an exact characterization of the latter model in terms of a weak version of a random access machine (RAM). We also compare the language recognition capability of a recurrent version of this model with that of deterministic finite automata and Turing machines.] 1999 Academic Press 1.
CONTRIBUTED ARTICLE Networks of Spiking Neurons: The Third Generation of Neural Network Models
, 1996
"... AbstractThe computational power of formal models for networks of spiking neurons is compared with that of other neural network models based on McCulloch Pitts neurons (i.e., threshold gates), respectively, sigmoidal gates. In particular it is shown that networks of spiking neurons are, with regard ..."
Abstract
 Add to MetaCart
(Show Context)
AbstractThe computational power of formal models for networks of spiking neurons is compared with that of other neural network models based on McCulloch Pitts neurons (i.e., threshold gates), respectively, sigmoidal gates. In particular it is shown that networks of spiking neurons are, with regard to the number of neurons that are needed, computationally more powerful than these other neural network models. A concrete biologically relevant function is exhibited which can be computed by a single spiking neuron (for biologically reasonable values of its parameters), but which requires hundreds of hidden units on a sigmoidal neural net. On the other hand, it is known that any function that can be computed by a small sigmoidal neural net can also be computed by a small network of spiking neurons. This article does not assume prior knowledge about spiking neurons, and it contains an extensive list of references to the currently available literature on computations in networks of spiking neurons and relevant results from neurobiology.
!()+, ./01 23456
, 1995
"... Computing the maximum bichromatic discrepancy is an interesting theoretical problem with important applications in computational learning theory, computational geometry and computer graphics. In this paper we give algorithms to compute the maximum bichromatic discrepancy for simple geometric ranges, ..."
Abstract
 Add to MetaCart
Computing the maximum bichromatic discrepancy is an interesting theoretical problem with important applications in computational learning theory, computational geometry and computer graphics. In this paper we give algorithms to compute the maximum bichromatic discrepancy for simple geometric ranges, including rectangles and halfspaces. In addition, we give extensions to other discrepancy problems. 1 Introduction The main theme of this paper is to present efficient algorithms that solve the problem of computing the maximum bichromatic discrepancy for axis oriented rectangles. This problem arises naturally in different areas of computer science, such as computational learning theory, computational geometry and computer graphics ([Ma], [DG]), and has applications in all these areas. In computational learning theory, the problem of agnostic PAClearning with simple geometric hypotheses can be reduced to the problem of computing the maximum bichromatic discrepancy for simple geometric ra...