. Low-dimensional representations of sensory signals are key to solving many of the computational problems encountered in high-level vision. Principal Component Analysis has been used in the past to derive practically useful compact representations for different classes of objects. One major objection to the applicability of PCA is that it invariably leads to global, nontopographic representations that are not amenable to further processing and are not biologically plausible. In this paper we present a new mathematical construction---Local Feature Analysis (LFA)---for deriving local topographic representations for any class of objects. The LFA representations are sparse-distributed and, hence, are effectively low-dimensional and retain all the advantages of the compact representations of the PCA. But unlike the global eigenmodes, they give a description of objects in terms of statistically derived local features and their positions. We illustrate the theory by using it to extract loca...

Abstract not found

Neurophysiological evidence is described, showing that some neurons in the macaque temporal cortical visual areas have responses that are invariant with respect to the position, size and view of faces and objects, and that these neurons show rapid processing and rapid learning. A theory is then described of how such invariant representations may be produced in a hierarchically organized set of visual cortical areas with convergent connectivity. The theory proposes that neurons in these visual areas use a modified Hebb synaptic modification rule with a short-term memory trace to capture whatever can be captured at each stage that is invariant about objects as the object changes in retinal position, size, rotation and view. Simulations are then described which explore the operation of the architecture. The simulations show that such a processing system can build invariant representations of objects.

... In this article, we show how trace learning could solve the problem of in-depth rotation-invariant object recognition by developing representations of the transforms that features undergo when they are on the surfaces of 3D objects. Moreover, we show that having learned how features on 3D objects transform geometrically as the object is rotated in depth, the network can correctly recognize novel 3D variations within a generic view of an object composed of a new combination of previously learned features. These results are demonstrated in simulations of a hierarchical network model (VisNet) of the visual system that show that it can develop representations useful for the recognition of 3D objects by forming perspective-invariant representations to allow generalization within a generic view.

Neurons in the ventral stream of the primate visual system exhibit responses to the images of objects which are invariant with respect to natural transformations such as translation, size, and view. Anatomical and neurophysiological evidence suggests that this is achieved through a series of hierarchical processing areas. In an attempt to elucidate the manner in which such representations are established, we have constructed a model of cortical visual processing which seeks to parallel many features of this system, specifically the multi-stage hierarchy with its topologically constrained convergent connectivity. Each stage is constructed as a competitive network utilising a modified Hebb-like learning rule, called the trace rule, which incorporates previous as well as current neuronal activity. The trace rule enables neurons to learn about whatever is invariant over short time periods (e.g. 0.5 s) in the representation of objects as the objects transform in the real world. The trace ru...

Imitation is a mechanism for the intergenerational transmission of acquired characteristics. Before explicit linguistic instruction, infants learn many of the skills, customs, and behaviour patterns of their culture through imitation. In imitating, infants use another's behaviours as a basis for their own, despite differences in body size, perspective of view, and modality through which self and other can be perceived. As ubiquitous and useful as imitation is, how imitation is accomplished poses one of the deeper puzzles in infancy.

In natural visual experience, different views of an object or face tend to appear in close temporal proximity as an animal manipulates the object or navigates around it, or as a face changes expression or pose. A set of simulations is presented which demonstrate how viewpoint invariant representations of faces can be developed from visual experience by capturing the temporal relationships among the input patterns. The simulations explored the interaction of temporal smoothing of activity signals with Hebbian learning (Foldi'ak, 1991) in both a feedforward layer and a second, recurrent layer of a network. The feedforward connections were trained by Competitive Hebbian Learning with temporal smoothing of the post-synaptic unit activities (Bartlett & Sejnowski, 1996). The recurrent layer was a generalization of a Hopfield network with a lowpass temporal filter on all unit activities. The combination of basic Hebbian learning with temporal smoothing of unit activities produced an attractor...

Abstract not found

In this report we review a large body of literature describing how experience affects recognition. Both neurophysiology and psychophysics provide clear evidence for the development of recognition over time. In particular, we show how perceptual learning in recognition tasks can be directly linked to learning in feature tuned inferotemporal lobe neurons in the primate brain. The environment as we experience it, is so structured that potentially very different images appearing in close temporal succession are likely to be views of the same object. We argue that this temporal structure forms the basis of a tendency (a prior in the sense of Bayesian Statistics) of the human visual system to associate images of objects together over short periods of time.

n Backward masking can potentially provide evidence of the time needed for visual processing, a fundamental constraint that must be incorporated into computational models of vision. Although backward masking has been extensively used psychophysically, there is little direct evidence for the effects of visual masking on neuronal responses. To investigate the effects of a backward masking paradigm on the responses of neurons in the temporal visual cortex, we have shown that the response of the neurons is interrupted by the mask. Under conditions when humans can just identify the stimulus, with stimulus onset asynchronies (SOA) of 20 msec, neurons in macaques respond to their best stimulus for approximately 30 msec. We now quantify the information that is available from the responses of single neurons under backward masking conditions when two to six faces were shown. We show that the information available is greatly decreased as the mask is brought closer to the stimulus. The decrease is more marked than the decrease in #ring rate because it is the selective part of the #ring that is especially attenuated by the mask, not the spontaneous #ring, and also because the neuronal response is more variable at short SOAs. However, even at the shortest SOA of 20 msec, the information available is on average 0.1 bits. This compares to 0.3 bits with only the 16-msec target stimulus shown and a typical value for such neurons of 0.4 to 0.5 bits with a 500msec stimulus. The results thus show that considerable information is available from neuronal responses even under backward masking conditions that allow the neurons to have their main response in 30 msec. This provides evidence for how rapid the processing of visual information is in a cortical area and provides a fundamental constra...