Approximating Optimal Information Transmission using Local Hebbian Algorithms in a Double Feedback Loop
نویسنده
چکیده
Maximising mutual information (MI) under various constraints has been suggested as a goal for neural networks in a perceptual system. Networks using Hebbian algorithms have been found to be suitable for optimising MI with either input or output noise. In this paper we show that a double feedback loop network, using local Hebbian algorithms, can approximate the characteristics required for optimizing MI with both input and output noise. This represents a better approximation than simply orthonormalising the principal subspace.
منابع مشابه
Presentation of quasi-linear piecewise selected models simultaneously with designing of bump-less optimal robust controller for nonlinear vibration control of composite plates
The idea of using quasi-linear piecewise models has been established on the decomposition of complicated nonlinear systems, simultaneously designing with local controllers. Since the proper performance and the final system close loop stability are vital in multi-model controllers designing, the main problem in multi-model controllers is the number of the local models and their position not payi...
متن کاملDouble loops flows and bidirectional Hebb's law in neural networks
This paper presents the double loop feedback model, which is used for structure and data flow modelling through reinforcement learning in an artificial neural network. We first consider physiological arguments suggesting that loops and double loops are widely spread in the exchange flows of the central nervous system. We then demonstrate that the double loop pattern, named a mental object, work...
متن کاملTHE EFFECTS OF INITIAL SAMPLING AND PENALTY FUNCTIONS IN OPTIMAL DESIGN OF TRUSSES USING METAHEURISTIC ALGORITHMS
Although Genetic algorithm (GA), Ant colony (AC) and Particle swarm optimization algorithm (PSO) have already been extended to various types of engineering problems, the effects of initial sampling beside constraints in the efficiency of algorithms, is still an interesting field. In this paper we show that, initial sampling with a special series of constraints play an important role in the conv...
متن کاملOn consensus algorithms for double-integrator dynamics without velocity measurements and with input constraints
This note deals with consensus strategy design for double-integrator dynamics. Specifically, we consider the case where the control inputs are required to be a priori bounded and the velocity (second state) is not available for feedback. Two different design methods are proposed. First, based on the auxiliary system approach, we propose a consensus algorithm that extends some of the existing re...
متن کاملA Hybrid Algorithm using Firefly, Genetic, and Local Search Algorithms
In this paper, a hybrid multi-objective algorithm consisting of features of genetic and firefly algorithms is presented. The algorithm starts with a set of fireflies (particles) that are randomly distributed in the solution space; these particles converge to the optimal solution of the problem during the evolutionary stages. Then, a local search plan is presented and implemented for searching s...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 1993