Are cortical models really bound by the "binding problem"?

By Maximilian Riesenhuber, Tomaso A. Poggio. 1999

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

On the Binding Problem in Artificial Neural Networks (2020, background): “For example, it has been debated whether synchrony is necessary (Merker, 2013; Riesenhuber and Poggio, 1999), fast enough (Ray and Maunsell, 2015; Palmigiano et al.”
Multiple Object Response Normalization in Monkey Inferotemporal Cortex (2005, methodology): “Moreover , although some contemporary models of the ventral stream use MAX operations (Riesenhuber and Poggio, 1999a), even these models do not predict complete clutter tolerance in IT (Riesenhuber and Poggio, 1999b).”
Hierarchical models of object recognition in cortex (1999, methodology): “Simulations showed that this model is capable of performing recognition in contex”
Modeling attention to salient proto-objects (2006, unknown): “We adopt the hierarchical model of object recognition by Riesenhuber and Poggio (1999b).”
Continuous transformation learning of translation invariant representations (2010, methodology): “…processing that is a property of cortical architecture, in which key principles agreed by many investigators (Fukushima 1980; Wallis and Rolls 1997; Riesenhuber and Poggio 1999a, b, 2000; Giese and Poggio 2003; Serre et al. 2007) include feedforward connectivity, local lateral inhibition within a…”
Models of object recognition (2000, background): “Conversely, in higher layers, where neurons are tuned to a greater number of more complex features, neurons show a greater degree of invariance, thus requiring fewer cells tuned to the same feature at different positions and scale”
Synchronization and pattern separation in spiking associative memories and visual cortical areas (2004, background): “, [154, 188, 191, 192, 51, 165, 150, 193, 168, 199, 187, 194, 148, 56, 163, 167, 59, 147, 205]) actually corresponds to a whole family of related problems.”
Semantics and the electrophysiology of meaning: Tense, aspect, event structure (2004, methodology): “See von der Malsburg [220] for a proposal in line with the binding hypothesis and Riesenhuber and Poggio [176] for an alternative approach.”
Dynamical principles in neuroscience (2006, background): “However, there is still criticism of the temporal binding hypothesis Ghose and Maunsell, 1999; Riesenhuber and Poggio, 1999 .”
Learning Optimized Features for Hierarchical Models of Invariant Object Recognition (2003, methodology): “Based on this C1 output, features were learned using sparse invariance, and then again a linear summation with these features in the S2 layer is followed by the MAX-pooling in the C2 layer.”
Attentional Selection for Object Recognition - A Gentle Way (2002, methodology): “Recognition of Attended Objects The recognition component is based on our previously published hierarchical model for object recognition HMAX [10, 11] that considers recognition as a feedforward process in the spirit of Fukushima’s Neocognitron [12].”
Physiologically Inspired Model for the Visual Recognition of Transitive Hand Actions (2013, unknown): “Thefirstmodel component follows closely well-known neural models for shape recognition in the ventral stream (Oram and Perrett, 1994; Riesenhuber and Poggio, 1999b; Rolls and Milward, 2000; Cadieu et al., 2007).”