This paper focuses on the multidirectional associative memory (MAM) neural networks with m fields which is more advanced to realize associative memory. Based on the Brouwer fixed point theorem and Dini upper right derivative, it is confirmed that the multidirectional associativememory neural network can have 3 equilibria and 2 equilibria of them are stable, where l is a parameter associated wit...

This paper considers the global exponential stability of delay neural networks with impulsive perturbations. By establishing a new impulsive delay inequality which is different from the earlier publication, we obtain some new sufficient conditions ensuring exponential stability of the equilibrium point for such neural networks. The neural networks model considered include the impulsive delay Ho...

The structure of complex biological and socio-economic networks affects the selective pressures or behavioural incentives of components in that network, and reflexively, the evolution/behaviour of individuals in those networks changes the structure of such networks over time. Such ‘adaptive networks’ underlie how gene-regulation networks evolve, how ecological networks self-organise, and how ne...

Recent studies of the statistical mechanics of neural network models of associative memory are reviewed. The paper discusses models which have an energy function but depart from the simple Hebb rule. This includes networks with static synaptic noise, dilute networks and synapses that are nonlinear functions of the Hebb ru1e (e.g., clipped networks). The properties of networks that ernp loy the ...

Due to feedback connections, recurrent neural networks (RNNs) are dynamic models. RNNs can provide more compact structure for approximating dynamic systems compared to feedforward neural networks (FNNs). For some RNN models such as the Hopfield model and the Boltzmann machine, the fixed-point property of the dynamic systems can be used for optimization and associative memory. The Hopfield model...

Auto-encoding is an important task which is typically realized by deep neural networks (DNNs) such as convolutional neural networks (CNN). In this paper, we propose EncoderForest (abbrv. eForest), the first tree ensemble based auto-encoder. We present a procedure for enabling forests to do backward reconstruction by utilizing the equivalent classes defined by decision paths of the trees, and de...

Minimization of energy or error functions has proved to be a useful principle in the design and analysis of neural networks and neural algorithms. A brief list of examples include: the backpropagation algorithm, the use of optimization methods in computational vision, the application of analog networks to the approximate solution of NP complete problems and the Hopfield model of associative mem...