Self-organizing Winner-Take-All networks
نویسندگان
چکیده
منابع مشابه
Self-organization of Multiple Winner-take-all Neural Networks
In this paper, analysis of the information content of discretely ring neurons in unsupervised neural networks is presented, where information is measured according to the network's ability to reconstruct its input from its output with minimum mean square Euclidean error. It is shown how this type of network can self-organise into multiple winner-take-all subnetworks, each of which tackles only ...
متن کاملDynamically-Adaptive Winner-Take-All Networks
Winner-Take-All (WTA) networks. in which inhibitory interconnections are used to determine the most highly-activated of a pool of unilS. are an important part of many neural network models. Unfortunately, convergence of normal WT A networks is extremely sensitive to the magnitudes of their weights, which must be hand-tuned and which generally only provide the right amount of inhibition across a...
متن کاملWinner-take-all networks with lateral excitation
In this paper we present two analog VLSI circuits that implement current mode winner-take-all (WTA) networks with lateral excitation. We describe their principles of operation and compare their performance to previously proposed circuits. The desirable properties of these circuits, namely compactness, low power consumption, collective processing and robustness to noisy inputs make them ideal fo...
متن کاملWinner-Take-All Discrete Recurrent Neural Networks
This paper proposes a discrete recurrent neural network model to implement winner-take-all function. This network model has simple organizations and clear dynamic behaviours. The dynamic properties of the proposed winner-take-all networks are studied in detail. Simulation results are given to show network performance. Since the network model is formulated as discrete time systems , it has advan...
متن کاملWinner-Take-All Autoencoders
In this paper, we propose a winner-take-all method for learning hierarchical sparse representations in an unsupervised fashion. We first introduce fully-connected winner-take-all autoencoders which use mini-batch statistics to directly enforce a lifetime sparsity in the activations of the hidden units. We then propose the convolutional winner-take-all autoencoder which combines the benefits of ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Frontiers in Neuroscience
سال: 2010
ISSN: 1662-453X
DOI: 10.3389/conf.fnins.2010.13.00064