Monotonic Transfer Function Research Articles

Sequence Processing Neural Network withQ-States Monotonic Transfer Function

Storage capacity as for retrieval of sequences of binary patterns is investigated for a fully connected neural network with Q (> 2)-states. By using a generating-function method of path-integral representation, we find that the network with Q-states monotonic transfer function retrieves more sequences of the stored patterns than that with a binary monotonic transfer function at zero temperature, if the control parameter is chosen optimally. We compare the results obtained by the analytic method with those by numerical simulations.

Layered neural networks with non-monotonic transfer functions

We investigate storage capacity and generalization ability for two types of fully connected layered neural networks with non-monotonic transfer functions; random patterns are embedded into the networks by a Hebbian learning rule. One of them is a layered network in which a non-monotonic transfer function of even layers is different from that of odd layers. The other is a layered network with intra-layer connections, in which the non-monotonic transfer function of inter-layer is different from that of intra-layer, and inter-layered neurons and intra-layered neurons are updated alternately. We derive recursion relations for order parameters for those layered networks by the signal-to-noise ratio method. We clarify that the storage capacity and the generalization ability for those layered networks are enhanced in comparison with those with a conventional monotonic transfer function when non-monotonicity of the transfer functions is selected optimally. We also point out that some chaotic behavior appears in the order parameters for the layered networks when non-monotonicity of the transfer functions increases.

Sequence Processing Neural Network with a Non-Monotonic Transfer Function

We investigate storage capacity and retrieval property for a synchronous fully connected neural network with a non-monotonic transfer function which retrieves sequences of patterns, by an analytic method and also by numerical simulations. Because of asymmetry of interactions and non-monotonicity of the transfer function, it is difficult to use conventional methods of the equilibrium statistical mechanics in order to investigate the network. We then use a generating-function method of path-integral representation, and obtain equations for dynamical order parameters in the stationary state. We clarify that the network with the non-monotonic transfer function retrieves more sequences of patterns than that with a monotonic transfer function at zero temperature when non-monotonicity of the transfer function is selected optimally. It is also clarified that some chaotic behavior appears in solutions for the equations of the dynamical order parameters when non-monotonicity of the transfer function increases. The ...

Retrieval phase diagrams of non-monotonic Hopfield networks

We investigate the retrieval phase diagrams of an asynchronous fully-connected attractor network with non-monotonic transfer function by means of a mean-field approximation. We find for the noiseless zero-temperature case that this non-monotonic Hopfield network can store more patterns than a network with monotonic transfer function investigated by Amit et al. Properties of retrieval phase diagrams of non-monotonic networks agree with the results obtained by Nishimori and Opris who treated synchronous networks. We also investigate the optimal storage capacity of the non-monotonic Hopfield model with state-dependent synaptic couplings introduced by Zertuche et el. We show that the non-monotonic Hopfield model with state-dependent synapses stores more patterns than the conventional Hopfield model. Our formulation can be easily extended to a general transfer function.

An Inherently Monotonic 7-Bit CMOS ADC for Video Applications

This paper describes a CMOS 7-bit flash analog-to-digital converter capable of operation at sample rates in excess of 30 megasamples per second (MSPS) with an analog bandwidth to /spl plusmn/1/2 least significant bit (Isb) of 5 MHz. The device has been realized on a 2-/spl mu/m double-layer metal CMOS process and takes advantage of the low power consumption available from CMOS logic. Circuit techniques have been employed to overcome most of the major problems inherent in flash converters and to guarantee a completely monotonic transfer function.