Attractor Neural Networks
نویسنده
چکیده
In this lecture I will present some models of neural networks that have been developed in the recent years. The aim is to construct neural networks which work as associative memories. Different attractors of the network will be identified as different internal representations of different objects. At the end of the lecture I will present a comparison among the theoretical results and some of the experiments done on real mammal brains.
منابع مشابه
بهبود بازشناسی مقاوم الگو در شبکه های عصبی بازگشتی جاذب از طریق به کارگیری دینامیک های آشوب گونه
In this paper, two kinds of chaotic neural networks are proposed to evaluate the efficiency of chaotic dynamics in robust pattern recognition. The First model is designed based on natural selection theory. In this model, attractor recurrent neural network, intelligently, guides the evaluation of chaotic nodes in order to obtain the best solution. In the second model, a different structure of ch...
متن کاملLearning in sparse attractor networks with inhibition
Attractor networks are important models for brain functions on a behavioral and physiological level, but learning on sparse patterns has not been fully explained. Here we show that the inclusion of the activity dependent effect of an inhibitory pool in Hebbian learning can accomplish learning of stable sparse attractors in both, continuous attractor and point attractor neural networks.
متن کاملAttractor Density Models with Application to Analyzing the Stability of Biological Neural Networks
An attractor modeling algorithm is introduced which draws upon techniques found in nonlineax dynamics and pattern recognition. The technique is motivated. by the need for quantitative measures that are able to assess the stability of biological neural networks which utilize nonlinear dynamics to process information. Attractor Density Models with Application to Analyzing the Stability of Biologi...
متن کاملAn Attractor-Based Complexity Measurement for Boolean Recurrent Neural Networks
We provide a novel refined attractor-based complexity measurement for Boolean recurrent neural networks that represents an assessment of their computational power in terms of the significance of their attractor dynamics. This complexity measurement is achieved by first proving a computational equivalence between Boolean recurrent neural networks and some specific class of ω-automata, and then t...
متن کاملAttractor Networks
Artificial neural networks (ANNs), sometimes referred to as connectionist networks, are computational models based loosely on the neural architecture of the brain. Over the past twenty years, ANNs have proven to be a fruitful framework for modeling many aspects of cognition, including perception, attention, learning and memory, language, and executive control. A particular type of ANN, called a...
متن کاملAttractor Neural Networks and Spatial Maps in Hippocampus
Attractor neural network theory has been proposed as a theory for long-term memory. Recent studies of hippocampal place cells, including a study by Leutgeb et al. in this issue of Neuron, address the potential role of attractor dynamics in the formation of hippocampal representations of spatial maps.
متن کامل