scholarly journals Competitive Coevolution through Evolutionary Complexification

2004 ◽  
Vol 21 ◽  
pp. 63-100 ◽  
Author(s):  
K. O. Stanley ◽  
R. Miikkulainen
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Arms Race ◽  
Network Architectures ◽  
Complex Problems ◽  
Wide Range ◽  
Competitive Coevolution ◽  
Neural Network Architectures ◽  
Complex Solutions ◽  
Fixed Structure

Two major goals in machine learning are the discovery and improvement of solutions to complex problems. In this paper, we argue that complexification, i.e. the incremental elaboration of solutions through adding new structure, achieves both these goals. We demonstrate the power of complexification through the NeuroEvolution of Augmenting Topologies (NEAT) method, which evolves increasingly complex neural network architectures. NEAT is applied to an open-ended coevolutionary robot duel domain where robot controllers compete head to head. Because the robot duel domain supports a wide range of strategies, and because coevolution benefits from an escalating arms race, it serves as a suitable testbed for studying complexification. When compared to the evolution of networks with fixed structure, complexifying evolution discovers significantly more sophisticated strategies. The results suggest that in order to discover and improve complex solutions, evolution, and search in general, should be allowed to complexify as well as optimize.

scholarly journals SURVEY ON EVOLVING DEEP LEARNING NEURAL NETWORK ARCHITECTURES

2019 ◽  
Vol 2019 (2) ◽  
pp. 73-82 ◽  
Author(s):  
Dr. Abul Bashar
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Neural Networks ◽  
Feature Extraction ◽  
Deep Learning ◽  
Human Performance ◽  
Deep Neural Networks ◽  
Network Architectures ◽  
Neural Network Architectures ◽  
Deep Learning Neural Network

The deep learning being a subcategory of the machine learning follows the human instincts of learning by example to produce accurate results. The deep learning performs training to the computer frame work to directly classify the tasks from the documents available either in the form of the text, image, or the sound. Most often the deep learning utilizes the neural network to perform the accurate classification and is referred as the deep neural networks; one of the most common deep neural networks used in a broader range of applications is the convolution neural network that provides an automated way of feature extraction by learning the features directly from the images or the text unlike the machine learning that extracts the features manually. This enables the deep learning neural networks to have a state of art accuracy that mostly expels even the human performance. So the paper is to present the survey on the deep learning neural network architectures utilized in various applications for having an accurate classification with an automated feature extraction.

scholarly journals Studying the Potential of Graphcore® IPUs for Applications in Particle Physics

2021 ◽  
Vol 5 (1) ◽  
Author(s):  
Samuel Maddrell-Mander ◽  
Lakshan Ram Madhan Mohan ◽  
Alexander Marshall ◽  
Daniel O’Hanlon ◽  
Konstantinos Petridis ◽  
...  
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Kalman Filter ◽  
Particle Physics ◽  
Processing Unit ◽  
Network Architectures ◽  
Track Reconstruction ◽  
Event Simulation ◽  
Scattering Correction ◽  
New Type

AbstractThis paper presents the first study of Graphcore’s Intelligence Processing Unit (IPU) in the context of particle physics applications. The IPU is a new type of processor optimised for machine learning. Comparisons are made for neural-network-based event simulation, multiple-scattering correction, and flavour tagging, implemented on IPUs, GPUs and CPUs, using a variety of neural network architectures and hyperparameters. Additionally, a Kálmán filter for track reconstruction is implemented on IPUs and GPUs. The results indicate that IPUs hold considerable promise in addressing the rapidly increasing compute needs in particle physics.

Sign in / Sign up

Export Citation Format

Share Document