Direct Fit to Nature: An Evolutionary Perspective on Biological and Artificial Neural Networks
نویسندگان
چکیده
منابع مشابه
Neural Networks in an Artificial Life Perspective
In the last few years several researchers within the Artificial Life and Mobile Robotics community used Artificial Neural Networks. Explicitly viewing Neural Networks in an Artificial Life perspective has a number of consequences that make research on what we will call Artificial Life Neural Networks (ALNNs) rather different from traditional connectionist research. The aim of the paper is to ma...
متن کاملOscillatorY Neural Networks: an Evolutionary Perspective
Motor patterns of the stomatogastric ganglion neurons of the shrimp Penaeus japonicus were studied in semi-isolated preparations of the complete stomatogastric nen伯us system. The oscillatory neural network can generate flexible motor patterns under the influence of extrinsic inputs from the higher center. Some neurons of the pyloric network are enhanced in their burstiness by excitatory synapti...
متن کاملMeta learning evolutionary artificial neural networks
In this paper, we present MLEANN (Meta-Learning Evolutionary Artificial Neural Network), an automatic computational framework for the adaptive optimization of artificial neural networks wherein the neural network architecture, activation function, connection weights; learning algorithm and its parameters are adapted according to the problem. We explored the performance of MLEANN and conventiona...
متن کاملEvolving Artificial Neural Networks through Evolutionary Programming
Artiicial neural network (ANN) architecture design has been one of the most tedious and diicult tasks in ANN applications due to the lack of satisfactory and systematic methods of designing a near optimal architecture. Evolutionary algorithms have been shown to be very eeective in evolving novel ANN architectures for various problems. This paper proposes a new automatic method for simultaneousl...
متن کاملEvolutionary reinforcement learning of artificial neural networks
In this article we describe EANT2, Evolutionary Acquisition of Neural Topologies, Version 2, a method that creates neural networks by evolutionary reinforcement learning. The structure of the networks is developed using mutation operators, starting from a minimal structure. Their parameters are optimised using CMA-ES, Covariance Matrix Adaptation Evolution Strategy, a derandomised variant of ev...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Neuron
سال: 2020
ISSN: 0896-6273
DOI: 10.1016/j.neuron.2019.12.002