A model of multiplicative neural responses in parietal cortex.

By Emilio Salinas, L. F. Abbott. 1996

Subfields: Natural Language Processing, Neuroscience

How researchers see this paper

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

In Natural Language Processing

In Neuroscience

Citations in the corpus

Maxout Networks (2013, background): “Note that the arguments in section 7 motivating the use of maxout also apply equally to rectiﬁed linear units (Salinas & Abbott, 1996; Hahnloser, 1998; Glorot et al., 2011).”
On the Convergence Rate of Training Recurrent Neural Networks (2018, background): “In fact, one of the earliest adoptions of ReLUs was on applications of RNNs for this purpose twenty years ago [21, 46].”
Inference and computation with population codes. (2003, background): “Salinas & Abbott (1995) proposed a similar scheme and subsequently showed that these gain fields could arise from a standard network model (Salinas & Abbott 1996).”
Fast Remapping of Sensory Stimuli onto Motor Actions on the Basis of Contextual Modulation (2004, methodology): “In particular, recurrent connections between output units could be used to reinforce and smooth the unimodal profile of activity, eliminating secondary bumps like those in Figure 3, a– c (Salinas and Abbott, 1996; Deneve et al., 1999).”
The Normalization Model of Attention (2009, unknown): “We remain agnostic as to the possible biophysical implementation of the attentional modulation, except to point out that biophysically plausible models of such multiplicative effects have been proposed (Abbott and Chance, 2005; Ardid et al., 2007; Chance et al., 2002; Doiron et al., 2001; Hahnloser ”
Discriminative Recurrent Sparse Auto-Encoders (2013, background): “…(DrSAE), comprising a recurrent encoder of rectified linear units (ReLU; Coates & Ng, 2011; Glorot, Bordes, & Bengio, 2011; Jarrett, et al., 2009; Nair & Hinton, 2010; Salinas & Abbott, 1996), connected to two linear decoders that reconstruct the input and predict its supervised classification.”
Deep Sparse Rectifier Neural Networks (2011, background): “Most previous studies of neural networks involving a rectifying activation function concern recurrent networks (Salinas and Abbott, 1996; Hahnloser, 1998).”
Separating Style and Content with Bilinear Models (2000, background): “At the physiological level, multiplicative neuronal interactions (Andersen, Essick, & Siegel, 1985; Olshausen, Anderson, & van Essen, 1993; Riesenhuber & Dayan, 1997), arising from nonlinear synaptic (Koch, 1997) or populationlevel ( Salinas & Abbott, 1993 ) mechanisms, have been proposed for visual”
Computational approaches to sensorimotor transformations (2000, background): “The addition of lateral connections does not alter in any way the computational properties of the basis function map; indeed, lateral connections can contribute to computation of the basis functions themselve”