Emergence of new signal-primitives in neural systems
... are recombinations of existing, prespecified symbols – there is no means by which new primitive symbols can be created by simply recombining existing ones. One does not create new alphabetical letter types by stringing together more and more existing letters – the new notations must be introduced fr ...
... are recombinations of existing, prespecified symbols – there is no means by which new primitive symbols can be created by simply recombining existing ones. One does not create new alphabetical letter types by stringing together more and more existing letters – the new notations must be introduced fr ...
Which Model to Use for the Liquid State Machine?
... In biological circuits a single neuron would not be able to process complex input information, and neural microcircuits constitute a computational base [1]. A new idea on microcircuit computing was suggested by Maass [2] and, since then, it has been called Liquid State Machine (LSM). In general, the ...
... In biological circuits a single neuron would not be able to process complex input information, and neural microcircuits constitute a computational base [1]. A new idea on microcircuit computing was suggested by Maass [2] and, since then, it has been called Liquid State Machine (LSM). In general, the ...
Neural computations that underlie decisions about sensory stimuli
... light, with some values being more likely than others when light is present (see Box 1). How do you use the value from the detector to decide if the light was present? This problem consists of deciding which hypothesis – light is present (h1) or light is absent (h2) – is most likely to be true given ...
... light, with some values being more likely than others when light is present (see Box 1). How do you use the value from the detector to decide if the light was present? This problem consists of deciding which hypothesis – light is present (h1) or light is absent (h2) – is most likely to be true given ...
Here - Statistical Analysis of Neuronal Data
... bias traditional measures using large batteries of simulated data. Traditional methods are biased by a number of features, including firing rate and dwell time in a cell s receptive field. To combat this, we have used a maximum likelihood estimation approach as a less biased and more sensitive way t ...
... bias traditional measures using large batteries of simulated data. Traditional methods are biased by a number of features, including firing rate and dwell time in a cell s receptive field. To combat this, we have used a maximum likelihood estimation approach as a less biased and more sensitive way t ...
artificial neural networks
... intelligent system over time. The most popular approaches to machine learning are artificial neural networks and genetic algorithms. This lecture is dedicated to neural networks. ...
... intelligent system over time. The most popular approaches to machine learning are artificial neural networks and genetic algorithms. This lecture is dedicated to neural networks. ...
Speciation by perception
... are necessary to obtain such high capacity (Haykin 1999). As an activation function for the output signal we used the logistic function f ðxÞ ¼ 1=1 þ eax which produces a sigmoid response. Compared to a simpler step function it makes it easier to determine in which direction weights should be adjus ...
... are necessary to obtain such high capacity (Haykin 1999). As an activation function for the output signal we used the logistic function f ðxÞ ¼ 1=1 þ eax which produces a sigmoid response. Compared to a simpler step function it makes it easier to determine in which direction weights should be adjus ...
Customer Segmentation based on Neural Network with Clustering
... much information as possible from a given data set while using the smallest number of features, not only can we save a great amount of computing time and cost, but also we can build a model that generalizes better to customer segmentation[7 ]. On the other hand, reducing the dimensionality of the in ...
... much information as possible from a given data set while using the smallest number of features, not only can we save a great amount of computing time and cost, but also we can build a model that generalizes better to customer segmentation[7 ]. On the other hand, reducing the dimensionality of the in ...
Two Kinds of Reverse Inference in Cognitive Neuroscience
... However, this article shows that it is crucial two distinguish between two different types of reverse inference. In the first kind, cognitive processes are inferred from the particular locations of neural activation observed in particular tasks. We examine these location-based inferences through a c ...
... However, this article shows that it is crucial two distinguish between two different types of reverse inference. In the first kind, cognitive processes are inferred from the particular locations of neural activation observed in particular tasks. We examine these location-based inferences through a c ...
A Learning Rule for the Emergence of Stable Dynamics and Timing
... other neurons. With training, the learning rule was effective in generating network activity. However, it did not converge to a steady state in which neurons stabilized at their target activity level. Instead, oscillatory behavior was observed. This behavior was observed in dozens of stimulations wi ...
... other neurons. With training, the learning rule was effective in generating network activity. However, it did not converge to a steady state in which neurons stabilized at their target activity level. Instead, oscillatory behavior was observed. This behavior was observed in dozens of stimulations wi ...
The Resilience of Computationalism - Philsci
... Neural processes are temporally constrained in real time, whereas computations are not; hence, neural processes are not computations (cf. Globus 1992, van Gelder 1998). This objection trades on an ambiguity between mathematical representation of time and real time. True, computations are temporally ...
... Neural processes are temporally constrained in real time, whereas computations are not; hence, neural processes are not computations (cf. Globus 1992, van Gelder 1998). This objection trades on an ambiguity between mathematical representation of time and real time. True, computations are temporally ...
Comparative performance of the FSCL neural net and K
... Given the success of neural networks in a variety of applications in engineering, such as speech and image quantization, it is natural to consider its application to similar problems in other domains. A related problem that arises in business is market segmentation for which Clustering techniques ar ...
... Given the success of neural networks in a variety of applications in engineering, such as speech and image quantization, it is natural to consider its application to similar problems in other domains. A related problem that arises in business is market segmentation for which Clustering techniques ar ...
Artificial neural network
In machine learning and cognitive science, artificial neural networks (ANNs) are a family of statistical learning models inspired by biological neural networks (the central nervous systems of animals, in particular the brain) and are used to estimate or approximate functions that can depend on a large number of inputs and are generally unknown. Artificial neural networks are generally presented as systems of interconnected ""neurons"" which exchange messages between each other. The connections have numeric weights that can be tuned based on experience, making neural nets adaptive to inputs and capable of learning.For example, a neural network for handwriting recognition is defined by a set of input neurons which may be activated by the pixels of an input image. After being weighted and transformed by a function (determined by the network's designer), the activations of these neurons are then passed on to other neurons. This process is repeated until finally, an output neuron is activated. This determines which character was read.Like other machine learning methods - systems that learn from data - neural networks have been used to solve a wide variety of tasks that are hard to solve using ordinary rule-based programming, including computer vision and speech recognition.