Mehmet Kerem Müezzinoglu

A new design method for the complex-valued multistate Hopfield associative memory

A method to store each element of an integral memory set M subset {1,2,...,K}/sup n/ as a fixed point into a complex-valued multistate Hopfield network is introduced. The method employs a set of inequalities to render each memory pattern as a strict local minimum of a quadratic energy landscape. Based on the solution of this system, it gives a recurrent network of n multistate neurons with complex and symmetric synaptic weights, which operates on the finite state space {1,2,...,K}/sup n/ to minimize this quadratic functional. Maximum number of integral vectors that can be embedded into the energy landscape of the network by this method is investigated by computer experiments. This paper also enlightens the performance of the proposed method in reconstructing noisy gray-scale images.

RBF-based neurodynamic nearest neighbor classification in real pattern space

Superposition of radial basis functions centered at given prototype patterns constitutes one of the most suitable energy forms for gradient systems that perform nearest neighbor classification with real-valued static prototypes. It is shown in this paper that a continuous-time dynamical neural network model, employing a radial basis function and a sigmoid multi-layer perceptron sub-networks, is capable of maximizing such an energy form locally, thus performing almost perfectly nearest neighbor classification, when initiated by a distorted pattern. The proposed design scheme allows for explicit representation of prototype patterns as network parameters, as well as augmenting additional or forgetting existing memory patterns. The dynamical classification scheme implemented by the network eliminates all comparisons, which are the vital steps of the conventional nearest neighbor classification process. The performance of the proposed network model is demonstrated on binary and gray-scale image reconstruction applications.

An energy function-based design method for discrete hopfield associative memory with attractive fixed points

An energy function-based autoassociative memory design method to store a given set of unipolar binary memory vectors as attractive fixed points of an asynchronous discrete Hopfield network (DHN) is presented. The discrete quadratic energy function whose local minima correspond to the attractive fixed points of the network is constructed via solving a system of linear inequalities derived from the strict local minimality conditions. The weights and the thresholds are then calculated using this energy function. If the inequality system is infeasible, we conclude that no such asynchronous DHN exists, and extend the method to design a discrete piecewise quadratic energy function, which can be minimized by a generalized version of the conventional DHN, also proposed herein. In spite of its computational complexity, computer simulations indicate that the original method performs better than the conventional design methods in the sense that the memory can store, and provide the attractiveness for almost all memory sets whose cardinality is less than or equal to the dimension of its elements. The overall method, together with its extension, guarantees the storage of an arbitrary collection of memory vectors, which are mutually at least two Hamming distances away from each other, in the resulting network.

A Boolean Hebb rule for binary associative memory design

A binary associative memory design procedure that gives a Hopfield network with a symmetric binary weight matrix is introduced in this paper. The proposed method is based on introducing the memory vectors as maximal independent sets to an undirected graph, which is constructed by Boolean operations analogous to the conventional Hebb rule. The parameters of the resulting network is then determined via the adjacency matrix of this graph in order to rind a maximal independent set whose characteristic vector is close to the given distorted vector. We show that the method provides attractiveness for each memory vector and avoids spurious memories whenever the set of given memory vectors satisfy certain compatibility conditions, which implicitly imply sparsity. The applicability of the design method is finally investigated by a quantitative analysis of the compatibility conditions.

Model Predictive Control with Reinforcement Learning for Drug Delivery in Renal Anemia Management

Treatment of chronic conditions often creates the challenge of an adequate drug administration. The intra- and inter-individual variability of drug response requires periodic adjustments of the dosing protocols. We describe a method, combining model predictive control for simulation of patient response and reinforcement learning for estimation of dosing strategy, to facilitate the management of anemia due to kidney failure

Reinforcement learning approach to individualization of chronic pharmacotherapy

Effective pharmacological therapy in chronic treatments poses many challenges to physicians. Individual response to treatment varies across patient populations. Furthermore, due to the prolonged character of the therapy, the response may change over time. A reinforcement learning-based framework is proposed for treatment individualization in the management of renal anemia. The approach is based on numerical simulation of the patient performed by Takagi-Sugeno fuzzy model and a radial basis function network implementation of an on-policy Q-learning critic. Simulation results demonstrate the potential of the proposed method to yield policies that achieve the therapeutic goal in individuals with different response characteristics.

Incorporating prior knowledge into Q-learning for drug delivery individualization

Individualization of drug delivery in treatment of chronic ailments is a challenge to the physician. Variability of response across patient population requires tailoring the dosing strategies to individuals needs. We have previously demonstrated the potential of reinforcement learning methods to support the physician in the management of anemia. In this paper, we propose the incorporation of prior knowledge into the learning mechanism to further improve the outcomes of the treatment.

Trajectory generation in guided spaces using NTG algorithm and artificial neural networks

This paper presents the preliminary results of nonlinear trajectory generation (NTG) using artificial neural networks (ANNs) as analytical data approximators. NTG framework designed at Caltech by Mark Milam et al. (2003) solves constrained nonlinear dynamic optimization problems in real time. A successful application of NTG on real-life problems with sampled data depends upon an accurate approximation scheme. Such an approximator is desired to have a compact architecture, a minimum number of design parameters, and a smooth continuously-differentiable input/output mapping. ANNs as universal approximators are known to possess these features, thus considered here as appropriate candidates for this task. The proposed cooperation of NTG and ANN is illustrated on an optimal control problem of generating realtime low observable trajectories for unmanned air vehicles in the presence of multiple radars

Projection-based gradient descent training of radial basis function networks

A new radial basis function (RBF) network training procedure that employs a linear projection technique along parameter search is proposed. To be applied simultaneously with the conventional center and/or weight adjustment methods, a gradient descent iteration on the width parameters of RBF units is introduced. The projection mechanism used by the procedure avoids negative width parameters and enables detection of redundant units, which can then be pruned from the network. Proposed training approach is applied to design a feedback neuro-controller for a nonlinear plant to track a desired trajectory.

A recurrent RBF network model for nearest neighbor classification

Superposition of radial basis functions centered at given prototype patterns constitutes one of the most suitable energy forms for gradient systems that perform nearest neighbor classification with real-valued static prototypes. It is shown in this paper that a continuous-time dynamical neural network model, employing a radial basis function and a sigmoid multilayer perceptron sub-networks, is capable of maximizing such an energy form locally, thus performing almost perfectly nearest neighbor classification, when initiated by a distorted pattern. The dynamical classification scheme implemented by the network eliminates all comparisons, which are the vital steps of the conventional nearest neighbor classification process. The performance of the proposed network model is demonstrated on image reconstruction applications.