tony/tensorneat-mend
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

add paper.txt

Browse Source
This commit is contained in:
wls2002
2023-07-27 00:52:30 +08:00
parent f61050d395
commit 809779d498
1 changed files with 9 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

18
paper.txt
View File

@@ -3,14 +3,14 @@ Neuroevolution is a subfield of artificial intelligence that
leverages evolutionary algorithms to generate and optimize leverages evolutionary algorithms to generate and optimize
artificial neural networks. This technique has proven to be artificial neural networks. This technique has proven to be
successful in solving a wide range of complex problems successful in solving a wide range of complex problems
across various domains. The NeuroEvolution of Augment- across various domains. The NeuroEvolution of Augmenting
ing Topologies (NEAT) is one of the most renowned al- Topologies (NEAT) is one of the most renowned algorithms
gorithms in neuroevolution. Characterized by its openness, in neuroevolution. Characterized by its openendedness, it
it starts with minimal networks and progressively evolves starts with minimal networks and progressively evolves both
both the topology and the weights of these networks to opti- the topology and the weights of these networks to optimize
mize performance. However, the acceleration techniques em- performance. However, the acceleration techniques employed
ployed in prevailing NEAT implementations typically rely on in prevailing NEAT implementations typically rely on par-
parallelism on CPUs, failing to harness the rapidly expand- allelism on CPUs, failing to harness the rapidly expand-
ing computational resources of today. To bridge this gap, ing computational resources of today. To bridge this gap,
we present NEATAX, an innovative framework that adapts we present NEATAX, an innovative framework that adapts
NEAT for execution on hardware accelerators. Built on top NEAT for execution on hardware accelerators. Built on top
@@ -24,4 +24,4 @@ minutes. These results demonstrate the potential of NEATAX
as a scalable and efficient solution for neuroevolution tasks, as a scalable and efficient solution for neuroevolution tasks,
paving the way for the future application of NEAT in more paving the way for the future application of NEAT in more
complex and demanding scenarios. NEATAX is available at complex and demanding scenarios. NEATAX is available at
https://github.com/WLS2002/neatax. https://github.com/WLS2002/neatax