A Note on Learning and Evolution in Neural Networks
نویسندگان
چکیده
Interactions between evolution and lifetime learning are of great interest to studies of adaptive behaviour both in the natural world and the field of evolutionary computation. This contribution revisits an earlier discovered observation that the average performance of a population of neural networks which are evolved to solve one task is improved by lifetime learning on a different task. Two existing, and very different, explanations of this phenomenon are summarised and examined. Experimental results are presented that demonstrate that neither of these explanations are sufficient to fully explain the phenomenon. A new explanation, together with experimental justification, is presented which describes the effect in terms of lifetime learning providing a buffer against the potentially deleterious effects of mutation.
منابع مشابه
A Differential Evolution and Spatial Distribution based Local Search for Training Fuzzy Wavelet Neural Network
Abstract Many parameter-tuning algorithms have been proposed for training Fuzzy Wavelet Neural Networks (FWNNs). Absence of appropriate structure, convergence to local optima and low speed in learning algorithms are deficiencies of FWNNs in previous studies. In this paper, a Memetic Algorithm (MA) is introduced to train FWNN for addressing aforementioned learning lacks. Differential Evolution...
متن کاملColor Matching of Blends Prepared From Black and White Fibers by Neural Networks (TECHNICAL NOTE)
The color of the blends of pre-colored fibers depends on the ratio of each fiber in the blends. Some theories have been introduced for color matching of blends of pre-colored fibers. Most however, are restricted in scope and accuracy. Kubelka and Munk presented the most applicable theory, which is still used in industry. In this work, the classical Kubelka-Munk method for color prediction of a ...
متن کاملReinforcement Learning in Neural Networks: A Survey
In recent years, researches on reinforcement learning (RL) have focused on bridging the gap between adaptive optimal control and bio-inspired learning techniques. Neural network reinforcement learning (NNRL) is among the most popular algorithms in the RL framework. The advantage of using neural networks enables the RL to search for optimal policies more efficiently in several real-life applicat...
متن کاملReinforcement Learning in Neural Networks: A Survey
In recent years, researches on reinforcement learning (RL) have focused on bridging the gap between adaptive optimal control and bio-inspired learning techniques. Neural network reinforcement learning (NNRL) is among the most popular algorithms in the RL framework. The advantage of using neural networks enables the RL to search for optimal policies more efficiently in several real-life applicat...
متن کاملOn the convergence speed of artificial neural networks in the solving of linear systems
Artificial neural networks have the advantages such as learning, adaptation, fault-tolerance, parallelism and generalization. This paper is a scrutiny on the application of diverse learning methods in speed of convergence in neural networks. For this aim, first we introduce a perceptron method based on artificial neural networks which has been applied for solving a non-singula...
متن کاملImage Backlight Compensation Using Recurrent Functional Neural Fuzzy Networks Based on Modified Differential Evolution
In this study, an image backlight compensation method using adaptive luminance modification is proposed for efficiently obtaining clear images.The proposed method combines the fuzzy C-means clustering method, a recurrent functional neural fuzzy network (RFNFN), and a modified differential evolution.The proposed RFNFN is based on the two backlight factors that can accurately detect the compensat...
متن کامل