Neuro-Symbolic Architectures

chevron-icon
RFP Proposals
Top
chevron-icon
project-presentation-img
Expert Rating 1.2
Kirmair Lima
Project Owner

Neuro-Symbolic Architectures

Expert Rating

1.2

Overview

Objective: Design hybrid DNN architectures that integrate symbolic reasoning with neurocognitive methods. Research Goals: Develop hybrid architectures combining symbolic logic and deep learning. Test models on real-world tasks such as semantic understanding and decision-making. Improve interpretability without compromising performance. Student Roles: Architect Developer: Designs hybrid DNN frameworks. Implementation Specialist: Implements models in Python or similar environments. Evaluation Analyst: Conducts experiments on real-world datasets. Literature Researcher: Reviews related works and best practices. Communications Lead: Prepares research papers and presentations.

RFP Guidelines

Neuro-symbolic DNN architectures

Complete & Awarded
  • Type SingularityNET RFP
  • Total RFP Funding $160,000 USD
  • Proposals 9
  • Awarded Projects 2
author-img
SingularityNET
Oct. 4, 2024

This RFP invites proposals to explore and demonstrate the use of neuro-symbolic deep neural networks (DNNs), such as PyNeuraLogic and Kolmogorov Arnold Networks (KANs), for experiential learning and/or higher-order reasoning. The goal is to investigate how these architectures can embed logic rules derived from experiential systems like AIRIS or user-supplied higher-order logic, and apply them to improve reasoning in graph neural networks (GNNs), LLMs, or other DNNs.

Proposal Description

Open Source Licensing

Apache License

Proposal Video

Not Avaliable Yet

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

  • Total Milestones

    5

  • Total Budget

    $80,000 USD

  • Last Updated

    4 Dec 2024

Milestone 1 - Hybrid Architecture Design

Description

Hybrid Architecture Design

Deliverables

Deliverable: Blueprint of proposed neuro-symbolic architecture models.

Budget

$30,000 USD

Success Criterion

Proposed architecture combines symbolic and neural approaches to exceed baseline performance in defined test cases.

Milestone 2 - Prototype Implementation

Description

Prototype Implementation

Deliverables

Deliverable: Functional prototypes for at least two hybrid architectures.

Budget

$20,000 USD

Success Criterion

Early implementations achieve at least 10% improvement in interpretability and predictive accuracy.

Milestone 3 - Validation and Performance Analysis

Description

Validation and Performance Analysis

Deliverables

Deliverable: Report on model accuracy, efficiency, and scalability tests.

Budget

$12,000 USD

Success Criterion

Models validated against benchmark datasets show performance gains in efficiency and reduced computational costs.

Milestone 4 - Model Refinement

Description

Model Refinement

Deliverables

Deliverable: Updated models with improved performance metrics.

Budget

$10,000 USD

Success Criterion

Developed architectures demonstrate scalability and adaptability for real-world industrial applications.

Milestone 5 - Final Publications and Knowledge Dissemination

Description

Final Publications and Knowledge Dissemination

Deliverables

Deliverable: Published papers and presentation materials for academic and industry conferences.

Budget

$8,000 USD

Success Criterion

Results published in reputable journals, with presentation at major conferences on AI or neural networks.

Join the Discussion (0)

Expert Ratings

Reviews & Ratings

Group Expert Rating (Final)

Overall

1.2

  • Feasibility 1.2
  • Desirabilty 1.2
  • Usefulness 1.2
  • Expert Review 1

    Overall

    1.0

    • Compliance with RFP requirements 1.0
    • Solution details and team expertise 1.0
    • Value for money 1.0
    Complete lack of details. Does not even mention proposed techniques, models or structures.

  • Expert Review 2

    Overall

    2.0

    • Compliance with RFP requirements 2.0
    • Solution details and team expertise 2.0
    • Value for money 2.0
    Proposal too vague

    Need more info to consider

  • Expert Review 3

    Overall

    1.0

    • Compliance with RFP requirements 1.0
    • Solution details and team expertise 1.0
    • Value for money 1.0
    No details regarding neurosymbolic integration

    No details are given except of the high level plan to integrate DNN and symbolic approaches, which is insufficient for this RFP. Furthermore: "Test models on real-world tasks such as semantic understanding and decision-making" These are real-world tasks?

  • Expert Review 4

    Overall

    1.0

    • Compliance with RFP requirements 1.0
    • Solution details and team expertise 1.0
    • Value for money 1.0
    An overly skeletal proposal without enough detail to allow serious evaluation

  • Expert Review 5

    Overall

    1.0

    • Compliance with RFP requirements 1.0
    • Solution details and team expertise 1.0
    • Value for money 1.0

    Very vague proposal with little to no detail.

feedback_icon