Evolving DNN Architectures

chevron-icon
RFP Proposals
Top
chevron-icon
project-presentation-img
Patrick Nercessian
Project Owner

Evolving DNN Architectures

Expert Rating

n/a

Overview

The goal of this project is to create a framework that uses evolutionary computation to design new neural network architectures for natural language prediction. The idea is to build on the success of transformers while exploring entirely new design possibilities that could outperform them. By simulating evolution—introducing variations, selecting the best-performing models, and iterating—the framework aims to uncover architectures that go beyond what human researchers have created. We aim to represent neural networks as directed acyclic graphs - and perform mutations and crossover on those representations. We also plan to allow mutations/crossover on model hyperparameters as well.

RFP Guidelines

Evolutionary algorithms for training transformers and other DNNs

Proposal Submission (4 days left)
  • Type SingularityNET RFP
  • Total RFP Funding $40,000 USD
  • Proposals 4
  • Awarded Projects n/a
author-img
SingularityNET
Aug. 12, 2024

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.

Proposal Description

Proposal Details Locked…

In order to protect this proposal from being copied, all details are hidden until the end of the submission period. Please come back later to see all details.

Proposal Video

Not Avaliable Yet

Check back later during the Feedback & Selection period for the RFP that is proposal is applied to.

  • Total Milestones

    4

  • Total Budget

    $40,000 USD

  • Last Updated

    27 Nov 2024

Milestone 1 - Framework Development

Description

1. Develop a mechanism to represent neural networks architectures (including transformers) as DAGs. 2. Implement hyperparameter mutation and recombination operators. 3. Implement architectural mutation and recombination operators which ensure valid architectures.

Deliverables

The creation of a framework which can create artificial neural networks from DAGs. By training on very small amounts of data we will also confirm the framework’s ability to generate valid architectures using mutation and recombination.

Budget

$12,000 USD

Milestone 2 - Initial Experiments

Description

1. Integrate evaluation and selection mechanisms using standard NLP datasets and fitness metrics. 2. Run initial evolutionary experiments. Try different neural network sizes and dataset sizes to generate data about how these experiments and architectures differ across scale.

Deliverables

An updated framework which is feature-complete for evolutionary runs. The output of the evolutionary experiments including perplexity on next-word prediction and other related evolutionary output metrics.

Budget

$8,000 USD

Milestone 3 - Refinement of Operators

Description

1. Develop advanced mutation and recombination operators incorporating biases toward favorable traits such as modularity or sparsity. 2. Run further experiments using these updated operators including creative population initialization (such as portions of the population having varying subsets or magnitudes of these new biases).

Deliverables

An updated framework which includes these advanced variation operators aimed to improve the search of the evolutionary algorithm.. The output of the evolutionary experiments including perplexity on next-word prediction and other related evolutionary output metrics.

Budget

$8,000 USD

Milestone 4 - Indentifying and Scaling Final Model

Description

1. Scale up the best-performing architectures for larger-scale training runs. 2. Compare the scaled models’ performance against known transformers of similar scale using training/test metrics and benchmark results. 3. Document findings and release codebase with comprehensive instructions and supporting documentation.

Deliverables

Larger-scale training runs to demonstrate the scalability of the best output model architectures from the evolutionary runs. Also the final codebase and report of our findings over the entire project.

Budget

$12,000 USD

Join the Discussion (0)

Expert Ratings

Reviews & Ratings

    No Reviews Avaliable

    Check back later by refreshing the page.

feedback_icon