Evolutionary algorithms for training transformers and other DNNs

Explore and demonstrate the use of evolutionary algorithms for training transformers and other DNNs

SingularityNET August 12, 2024

Type

SingularityNET RFP

Total RFP Funding

$40,000 USD

Proposals

Awarded Projects

Content

Short summary
Main purpose

Overview

Proposal Winners
Single
Max Funding / Proposal
$40,000 USD

Awarded Funding History

AWARDED PROJECTS	FUNDING AWARDED	ACTION
Evolving DNN Architectures	$ 40000 USD	View

Short summary

Explore and demonstrate the use of evolutionary methods (EMs) for training various DNNs including transformer networks. Such exploration could include using EMs to determine model node weights, and/or using EMs to evolve DNN/LLM architectures. Covariance Matrix Adaptation Evolution Strategy (CMA-ES) is an example of one very promising evolutionary method among others.

Main purpose

The primary objectives of this EM (Evolutionary Methods) exploration and demonstration RFP are to determine the effectiveness of either or both of the following:

EMs for updating node weights;
EMs for evolving DNN architectures.

0 proposals

No Proposals Avaliable

Check back later by refreshing the page.

1 Projects

Evolving DNN Architectures

Type SingularityNET RFP
Funding Awarded $40,000 USD
RFP Guidelines Evolutionary algorithms for training transformers and other DNNs

patricknercessian

Nov. 27, 2024

Join the Discussion (0)

Matt_Ikle

RFP Owner

View Profile

PROJECTS

Rounds

RFPS

Deep Projects

Collaborations

AI PLATFORM