Biomaterial Database

Fast sigmoidal networks via spiking neurons. 1997

W Maass

Institute for Theoretical Computer Science, Technische Universitaet Graz, Austria.

We show that networks of relatively realistic mathematical models for biological neurons in principle can simulate arbitrary feedforward sigmoidal neural nets in a way that has previously not been considered. This new approach is based on temporal coding by single spikes (respectively by the timing of synchronous firing in pools of neurons) rather than on the traditional interpretation of analog variables in terms of firing rates. The resulting new simulation is substantially faster and hence more consistent with experimental results about the maximal speed of information processing in cortical neural systems. As a consequence we can show that networks of noisy spiking neurons are "universal approximators" in the sense that they can approximate with regard to temporal coding any given continuous function of several variables. This result holds for a fairly large class of schemes for coding analog variables by firing times of spiking neurons. This new proposal for the possible organization of computations in networks of spiking neurons systems has some interesting consequences for the type of learning rules that would be needed to explain the self-organization of such networks. Finally, the fast and noise-robust implementation of sigmoidal neural nets by temporal coding points to possible new ways of implementing feedforward and recurrent sigmoidal neural nets with pulse stream VLSI.

UI	MeSH Term	Description	Entries
D007858	Learning	Relatively permanent change in behavior that is the result of past experience or practice. The concept includes the acquisition of knowledge.	Phenomenography
D009474	Neurons	The basic cellular units of nervous tissue. Each neuron consists of a body, an axon, and dendrites. Their purpose is to receive, conduct, and transmit impulses in the NERVOUS SYSTEM.	Nerve Cells,Cell, Nerve,Cells, Nerve,Nerve Cell,Neuron
D005071	Evoked Potentials	Electrical responses recorded from nerve, muscle, SENSORY RECEPTOR, or area of the CENTRAL NERVOUS SYSTEM following stimulation. They range from less than a microvolt to several microvolts. The evoked potential can be auditory (EVOKED POTENTIALS, AUDITORY), somatosensory (EVOKED POTENTIALS, SOMATOSENSORY), visual (EVOKED POTENTIALS, VISUAL), or motor (EVOKED POTENTIALS, MOTOR), or other modalities that have been reported.	Event Related Potential,Event-Related Potentials,Evoked Potential,N100 Evoked Potential,P50 Evoked Potential,N1 Wave,N100 Evoked Potentials,N2 Wave,N200 Evoked Potentials,N3 Wave,N300 Evoked Potentials,N4 Wave,N400 Evoked Potentials,P2 Wave,P200 Evoked Potentials,P50 Evoked Potentials,P50 Wave,P600 Evoked Potentials,Potentials, Event-Related,Event Related Potentials,Event-Related Potential,Evoked Potential, N100,Evoked Potential, N200,Evoked Potential, N300,Evoked Potential, N400,Evoked Potential, P200,Evoked Potential, P50,Evoked Potential, P600,Evoked Potentials, N100,Evoked Potentials, N200,Evoked Potentials, N300,Evoked Potentials, N400,Evoked Potentials, P200,Evoked Potentials, P50,Evoked Potentials, P600,N1 Waves,N2 Waves,N200 Evoked Potential,N3 Waves,N300 Evoked Potential,N4 Waves,N400 Evoked Potential,P2 Waves,P200 Evoked Potential,P50 Waves,P600 Evoked Potential,Potential, Event Related,Potential, Event-Related,Potential, Evoked,Potentials, Event Related,Potentials, Evoked,Potentials, N400 Evoked,Related Potential, Event,Related Potentials, Event,Wave, N1,Wave, N2,Wave, N3,Wave, N4,Wave, P2,Wave, P50,Waves, N1,Waves, N2,Waves, N3,Waves, N4,Waves, P2,Waves, P50
D000200	Action Potentials	Abrupt changes in the membrane potential that sweep along the CELL MEMBRANE of excitable cells in response to excitation stimuli.	Spike Potentials,Nerve Impulses,Action Potential,Impulse, Nerve,Impulses, Nerve,Nerve Impulse,Potential, Action,Potential, Spike,Potentials, Action,Potentials, Spike,Spike Potential
D000465	Algorithms	A procedure consisting of a sequence of algebraic formulas and/or logical steps to calculate or determine a given task.	Algorithm
D016014	Linear Models	Statistical models in which the value of a parameter for a given value of a factor is assumed to be equal to a + bx, where a and b are constants. The models predict a linear regression.	Linear Regression,Log-Linear Models,Models, Linear,Linear Model,Linear Regressions,Log Linear Models,Log-Linear Model,Model, Linear,Model, Log-Linear,Models, Log-Linear,Regression, Linear,Regressions, Linear
D016571	Neural Networks, Computer	A computer architecture, implementable in either hardware or software, modeled after biological neural networks. Like the biological system in which the processing capability is a result of the interconnection strengths between arrays of nonlinear processing nodes, computerized neural networks, often called perceptrons or multilayer connectionist models, consist of neuron-like units. A homogeneous group of units makes up a layer. These networks are good at pattern recognition. They are adaptive, performing tasks by example, and thus are better for decision-making than are linear learning machines or cluster analysis. They do not require explicit programming.	Computational Neural Networks,Connectionist Models,Models, Neural Network,Neural Network Models,Neural Networks (Computer),Perceptrons,Computational Neural Network,Computer Neural Network,Computer Neural Networks,Connectionist Model,Model, Connectionist,Model, Neural Network,Models, Connectionist,Network Model, Neural,Network Models, Neural,Network, Computational Neural,Network, Computer Neural,Network, Neural (Computer),Networks, Computational Neural,Networks, Computer Neural,Networks, Neural (Computer),Neural Network (Computer),Neural Network Model,Neural Network, Computational,Neural Network, Computer,Neural Networks, Computational,Perceptron