An analysis of the gamma memory in dynamic neural networks

By José Carlos Príncipe, J. Kuo, S. Çelebi. 1994

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Lifelong Learning of Spatiotemporal Representations With Dual-Memory Recurrent Self-Organization (2018, methodology): “The Gamma-GWR model (Parisi et al., 2017) is a recurrent extension of the Grow-When-Required (GWR) self-organizing network (Marsland et al., 2002) that embeds a Gamma memory (Principe et al., 1994) for representing short-term temporal relations.”
Frequency-sensitive competitive learning for scalable balanced clustering on high-dimensional hyperspheres (2004, background): “Further note that this particular form of the likelihood function is due to our choice of the proportionality constant, and other values of the constant will give slightly different forms for this likelihood function.”
Gamma-Filter Self-Organizing Neural Networks for Time Series Analysis (2011, background): “The mean memory depth for a Gamma memory of order-K becomes [ 16 ],[17],”
Stability and Synchronization of Discrete-Time Markovian Jumping Neural Networks With Mixed Mode-Dependent Time Delays (2009, background): “Distributed delays over a certain duration of time have been introduced in [30] and [36] such that the distant past has less influence compared to the recent behavior of the state.”
Global Asymptotical Stability of Recurrent Neural Networks With Multiple Discrete Delays and Distributed Delays (2006, background): “Since a neural network usually has a spatial nature due to the presence of an amount of parallel pathways of a variety of axon sizes and lengths, it is desired to model them by introducing continuously distributed delays over a certain duration of time, such that the distant past has less influence ”