Nonlinear neural networks: Principles, mechanisms, and architectures

By Stephen Grossberg. 1988

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

Learning in Nonstationary Environments: A Survey (2015, background): “The latter two points can be summarized by the so-called stability-plasticity dilemma [82], which refers to the ability of a model either to retain existing knowledge or learn new knowledge, but not being able to do both at the same time equally well.”
Adaptive Resonance Theory: How a brain learns to consciously attend, learn, and recognize a changing world (2013, methodology): “…learning to continually update spatial maps and sensory–motor gains as our bodily parameters change through time (Bullock, Cisek, & Grossberg, 1998; Bullock & Grossberg, 1988; Gaudiano & Grossberg, 1991;Georgopoulos, Kalaska, Caminiti, &Massey, 1982; Georgopoulos, Schwartz, & Kettner, 1986).”
Adaptive Machine Learning for Credit Card Fraud Detection (2015, background): “This is known as the stability-plasticity dilemma [151].”
Self-Organizing Feature Maps for Modeling and Control of Robotic Manipulators (2003, methodology): “This would allow the comparison with other unsupervised models, such as the VITE (Bullock and Grossberg, 1988), the VAM (Gaudiano and Grossberg, 1991) and the DIRECT models (Bullock et al., 1993) in more common grounds.”
Incremental Learning Using a Grow-and-Prune Paradigm With Efficient Neural Networks (2019, background): “However, aiming to achieve these two goals simultaneously suffers from the well-known stability-plasticity dilemma [36]: a purely stable model is able to conserve all prior knowledge, but cannot accommodate any new data or information, whereas a completely plastic model has the opposite problem.”
(Corr. to) Delay-dependent exponential stability analysis of delayed neural networks: an LMI approach (2002, background): “Such a global limit property, pointed out in Cohen and Grossberg (1983) and Grossberg (1988), wad obtained by considering some Lyapunov functions under the assumption that the connection matrix is symmetrical and the activation functions are continuous, differentiable, monotonically nondecreasing,…”
Connectionist models of recognition memory: constraints imposed by learning and forgetting functions. (1990, background): “Although there has been work on such neurally inspired models for several years (e.g., J. A. Anderson, 1972, 1973; J. A. Anderson & Hinton, 1981; J. A. Anderson, Silverstein, Ritz, & Jones, 1977; Grossberg , 1980, 1988; Kohonen, 1978), recent interest has been fueled by the finding that earlier…”
Fundamentals of Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM) Network (2018, background): “It has also been noted that the Additive Model generalizes the Hopfield model [23], which, while rooted in biological plausibility, has been influential in physics and engineering [18, 19].”
A neural network approach to complete coverage path planning (2004, methodology): “This model provided the foundation of the shunting model and led to many model variations and applications [31], [33], [ 35 ].”
Connectionist models of development (2003, background): “In order to ensure that the L1→L2 and L2→L1 weights are approximately symmetric, the normalization was done over incoming weights for L1→L2 projections, and over outgoing weights for L2→L1 projections (Grossberg, 1988).”
Neurodynamics of biased competition and cooperation for attention: a model with spiking neurons. (2005, methodology): “…Usher and Niebur (1996) introduced an early model of biased competition to explain the attentional effects in neural responses observed in the inferotemporal cortex, and this was followed by a model for V2 and V4 by Reynolds et al. (1999) based on the shunting equations of Grossberg (1988).”
Hierarchical models of object recognition in cortex (1999, unknown): “[35] Grossberg, S.”
Learn++: an incremental learning algorithm for supervised neural networks (2001, background): “bility–plasticity dilemma[1], one of the fundamental problems in knowledge management (KM): Some information may have”
Merging chrominance and luminance in early, medium, and late fusion using Convolutional Neural Networks (2015, methodology): “This architecture was a special case of the Cohen and Grossberg neural network that was finally called Hopfield networks (see also [Hopfield, 1984] and a historical summary made by Grossberg [Grossberg, 1988]).”
Neural networks and principal component analysis: Learning from examples without local minima (1989, background): “We shall assume that the reader is familiar with the basic concepts of the field; general reviews, complements , and references can be found in Rumelhart, McClelland, and the PDP Research Group (1986a), Lippman (1987), and Grossberg (1988).”
Bio inspired computing - A review of algorithms and scope of applications (2016, background): “AC CE PT ED M AN US CR IP T Neural Networks (Grossberg, 1988) are often defined as adaptive non-linear data processing algorithms that combines multiple processing units connected in a network in different layers.”