— The capacity of an order-d associative memory model is O(N d /logN) where N is the memory size in bit. In contrast, the capacity of the Hopfield network is limited to O(N/logN). Among higher order associative memory models (d > 1), the second order memory (d = 2) has attractive properties: a relatively small implementation cost of O(N 2), a small number of spurious states, and the presence of...

We propose a convolutional recurrent neural network, with Winner-Take-All dropout for high dimensional unsupervised feature learning in multi-dimensional time series. We apply the proposedmethod for object recognition with temporal context in videos and obtain better results than comparable methods in the literature, including the Deep Predictive Coding Networks previously proposed by Chalasani...

This article initiates a rigorous theoretical analysis of the computational power of circuits that employ modules for computing winner-take-all. Computational models that involve competitive stages have so far been neglected in computational complexity theory, although they are widely used in computational brain models, artificial neural networks, and analog VLSI. Our theoretical analysis shows...

Understanding the sequence generation and learning mechanisms used by recurrent neural networks in the nervous system is an important problem that has been studied extensively. However, most of the models proposed in the literature are either not compatible with neuroanatomy and neurophysiology experimental findings, or are not robust to noise and rely on fine tuning of the parameters. In this ...

'Winner-take-all' networks are an important theoretical construct in visual neuroscience. An implication of winner-take-all networks is that a stimulus that wins the competition for selection receives maximal activation and will be consciously perceived, even when selection was incorrect. In this study, competition was induced between physically presented ('real') and self-constructed ('illusor...

Winner-take-all (WTA) structures are currently used in massively parallel (connectionist) networks to represent competitive behavior among sets of alternative hypotheses. However, this form of competition might be too rigid and not be appropriate for certain applications. For example, applications that involve noisy and erroneous inputs might mislead W T A structures into selecting a wrong outc...

"Winner-Take-All"-markets, i.e. markets in which the relative and not the absolute performance is decisive, have gained in importance. Such markets have a tendency to provoke inefficiently many entries. We investigate the functioning of such markets with the help of experiments and show that there are even more inefficient entries than predicted by the Nash equilibrium. Moreover, this effect in...

Compared to previous studies of competition with participants' direct involvement, the current study for the first time investigated the influence of competitive outcomes on attentional bias from a perspective of an onlooker. Two simple games were employed: the Rock-Paper-Scissors game (Experiment 1) in which the outcome is based on luck, and Arm-wrestling (Experiment 2), in which the outcome i...

The finding that attention can encompass several non-contiguous items at once challenges the current models of visual search based on a winner-take-all mechanism assuming the selection of a single object. It has been proposed instead that attentional guidance involves mechanisms selecting all relevant items simultaneously. In order to test this hypothesis, we studied attentional allocation duri...

John Maynard Keynes once compared investing in the stock market to picking the winner of a beauty contest. In each case, it’s not who you think will win, but who you think others will pick. The same characterization increasingly applies to a student’s choice among universities. This choice depends much less now on what any individual student may think, and much more on what panels of experts th...