Complexity at the neuronal level

A Temporal Stability Approach to Position and Attention-Shift-Invariant Recognition

Incorporation of visual-related self-action signals can help neural networks learn invariance. We describe a method that can produce a network with invariance to changes in visual input caused by eye movements and covert attention shifts. Training of the network is controlled by signals associated with eye movements and covert attention shifting. A temporal perceptual stability constraint is used to drive the output of the network toward remaining constant across temporal sequences of saccadicmotions and covert attention shifts. We use a four-layer neural network model to perform the position-invariant extraction of local features and temporal integration of invariant presentations of local features in a bottom-up structure. We present results on both simulated data and real images to demonstrate that our network can acquire both position and attention shift invariance.

Spatial attention and latencies of saccadic eye movements

Recent theories of visual attention, such as the oculomotor readiness theory of Klein (1980) (Does oculomotor readiness mediate cognitive control of the visual attention. In: R. Nickerson, Attention and performance, Hillsdale: Erlbaum), the premotor theory of Rizzolati (1983) (Mechanisms of selective attention in mammals. In: J.P. Ewart, R.R. Capranica, D.J. Ingle, Advances in vertebrate Neuroethology (pp. 261-297). New York: Plenum) and the sequential attention theory of Henderson (1992) (Visual attention and eye movement control during reading and scene perception. In K. Rayner, Eye movements and visual cognition (260-283). New York: Springer-Verlag), propose a link between shifts in spatial attention and the generation of saccadic eye movements. In this paper we show that a winner-take-all model of spatial attention, combined with a simple model for the link between attention and eye movements, can account for the variation in saccadic latency observed in many oculomotor phenomena. These phenomena include the gap effect (Saslow M.G. (1967). Effects of components of displacement-step stimuli upon latency for saccadic eye movement. Journal of the Optical Society of America, 57, 1024-1029), the effect of target jumps on saccadic latency (Becker W. & Jurgens R. (1979). An analysis of the saccadic system by means of double step stimuli. Vision Research, 19, 967-983), the increase of saccadic latency as target eccentricity drops (Kalesnykas R.P. & Hallett P.E. (1994). Retinal eccentricity and the latency of eye saccades. Vision Research, 34, 517-531), and the modulation of saccadic accuracy using target predictability and saccadic latency (Coëffé C. & O'Regan J.K. (1987). Reducing the influence of non-target stimuli on saccade accuracy: predictability and latency effects. Vision Research, 27 (2), 227-240).