Musonda Bemba

Project Owner

Experiential Reasoning and Interpretability

Expert Rating

n/a

Type SingularityNET RFP
Funding Request $50,000 USD
RFP Guidelines Neural-symbolic DNN architectures

Overview

This proposal aims to develop neuro-symbolic deep neural network (DNN) architectures that combine the experiential learning capabilities of Kolmogorov–Arnold Networks (KANs) with the symbolic logic representation power of PyNeuraLogic. The objective is to achieve higher-order reasoning, interpretability, and real-world applicability in AGI systems. The approach will be integrated with the PRIMUS/Hyperon framework, providing a hybrid system that balances statistical learning and symbolic inference.

Project Tags:
Community and Collaboration

RFP Guidelines

Neural-symbolic DNN architectures

Complete & Awarded

Type SingularityNET RFP
Total RFP Funding $160,000 USD
Proposals 17
Awarded Projects 1

SingularityNET

Apr. 14, 2025

SingularityNET

rfp owner

Neural-symbolic DNN architectures

Complete & Awarded

This RFP invites proposals to explore and demonstrate the use of neural-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. Bids are expected to range from $40,000 - $100,000.

View Full RFP

Proposal Description

Project details

Despite remarkable advances in large language models (LLMs) and deep neural networks (DNNs), these systems still lack transparent, interpretable reasoning mechanisms and true generalization across contexts. Current architectures are often black-box systems, limited in their ability to explain or adapt their decisions in a symbolic or logically structured manner. This hinders their deployment in mission-critical and ethically sensitive environments where trust, traceability, and causal understanding are essential.

Symbolic AI, on the other hand, offers interpretability and reasoning but struggles with scalability and adaptability in uncertain or data-rich environments. Bridging the gap between these paradigms—neural and symbolic—remains an open challenge at the heart of advancing Artificial General Intelligence (AGI).

This project aims to design and prototype novel neuro-symbolic DNN architectures by integrating:

Kolmogorov–Arnold Networks (KANs) – for experiential learning, functional decomposition, and smooth generalization.
PyNeuraLogic – for logic-based symbolic inference and rule-based learning.
Integration with the PRIMUS/Hyperon AGI platform – to enable higher-order cognition and scalable reasoning.

The specific goals are:

Build modular and hybrid neuro-symbolic architectures that combine continuous and discrete learning.
Demonstrate transparent symbolic rule extraction from KAN-learned models using PyNeuraLogic.
Benchmark performance on reasoning, generalization, and interpretability tasks.
Develop and test plugins to connect with PRIMUS/Hyperon (MeTTa and ECAN subsystems).

Activity Summary

Milestones

3

Total

Discussion

0

Total Comments

Reviews

0

Total Posted

Project Team

1

Total People

Total Milestones
3
Total Budget
$50,000_USD
Last Updated
23 Apr 2025

Milestone 1 - Foundational Architecture& KAN-PyNeuraLogic Design

Description

KANs on Steroids: Containerize KAN models with NVIDIA Triton for <200ms GPU-accelerated inference exposing gRPC endpoints for PyNeuraLogic handshake. Logic Bloodline: Build an idempotent REST->gRPC proxy layer (Envoy) that auto-retries on translation hiccups tagged with OpenTelemetry spans for distributed tracing. Data Firehose: Implement Apache Kafka topics for streaming KAN outputs (Avro-serialized) to PyNeuraLogic workers.

Deliverables

Production-grade Helm charts with HPA thresholds (CPU:60% Mem:80%) Terraform module for AWS Inferentia2 deployment (shows cost-performance tradeoffs) Annotated Swagger docs with x-kong-credential extensions for API gateway integration

Budget

$20,000 USD

Success Criterion

≥99.9% API uptime under 50+ RPS sustained load for 72h (Grafana alerts on breaching 300ms p95 latency). Zero container restarts due to OOM during Kafka Avro serialization bursts (promql: container_memory_working_set_bytes{container="kan-grpc"} > 3GB).

Milestone 2 - Symbolic-Neuro Feedback Loop

Description

Feedback Armor: Symbolic reasoning outcomes trigger Argo Workflows to retrain KANs via PyTorch Lightning with a CircuitBreakerException fallback to frozen models. Grounding Grpc: Protobuf schemas enforce type safety during neural→symbolic transformations rejecting malformed Datalog rules (>95% validation coverage).

Deliverables

Signed SBOMs (Syft+SPDX) for all container images OPA policies enforcing feedback loop SLAs (e.g. "symbolic corrections must propagate to KANs within 2s p99")

Budget

$15,000 USD

Success Criterion

Feedback loops process 1K TPS with <1% circuit breaker tripping during chaos tests (Gremlin API blackholes validated). All symbolic corrections achieve sub-2s P99 propagation to KAN weights, verified by OpenTelemetry pyneuralogic_feedback_latency_seconds histograms.

Milestone 3 - PRIMUS/Hyperon Agent Demo

Description

Decision Auditing: Integrate OpenSearch to log neuro-symbolic choice rationales with differential privacy noise (ε=0.5). Zero-Touch Prod: Agent upgrades use Argo Rollouts with automated hypothesis testing (95% confidence interval on reward function deltas).

Deliverables

Istio Wasm plugin for runtime symbolic rule validation Tekton pipeline generating ONNX+PyNeuraLogic artifacts for Edge deployments

Budget

$15,000 USD

Success Criterion

Agent rollbacks from failed neuro-symbolic states complete in <3m (LitmusChaos metrics tagged with argo_rollout_phase:retry). Differential privacy noise (ε=0.5) maintains 95% confidence intervals on reward deltas during live hypothesis testing (Prometheus hypothesis_test_confidence gauge).

Join the Discussion (0)

Expert Ratings

Reviews & Ratings

No Reviews Avaliable

Check back later by refreshing the page.

The weighted average of the 4 perspectives Overall

0.0
Each RFP defines a maximum allowed budget, but teams can differentiate their proposal by offering a solution with a lower budget or a wider scope.Value for money

0.0
This rating indicates compliance to 'Must haves' but also adaptation of 'Nice to haves' and Non-functional requirements defined in the RFP.Compliance with RFP requirements

0.0
RFPs will offer varying degrees of freedom. This rating indicates the quality of the team's specific solution ideas, the provided details, and the reviewer's confidence in the team's ability to execute.Solution details and team expertise

0.0

Review Headline

0 /50 chars

Review Summary

0 /5000 chars

The weighted average of the 4 perspectives Overall

0.0
Each RFP defines a maximum allowed budget, but teams can differentiate their proposal by offering a solution with a lower budget or a wider scope.Value for money

0.0
This rating indicates compliance to 'Must haves' but also adaptation of 'Nice to haves' and Non-functional requirements defined in the RFP.Compliance with RFP requirements

0.0
RFPs will offer varying degrees of freedom. This rating indicates the quality of the team's specific solution ideas, the provided details, and the reviewer's confidence in the team's ability to execute.Solution details and team expertise

0.0

Review Headline

0 /50 chars

0 /5000 chars

Warning: Adding final group rating for this project will prevent expert users from adding new or editing existing reviews

Reviews and Ratings in Deep Funding are structured in 4 categories. This will ensure that the reviewer takes all these perspectives into account in their assessment and it will make it easier to compare different projects on their strengths and weaknesses. Overall (Primary) This is an average of the 4 perspectives. At the start of this new process, we are assigning an equal weight to all categories, but over time we might change this and make some categories more important than others in the overall score. (This may even be done retroactively). Feasibility (secondary) This represents the user\'s assessment of whether the proposed project is theoretically possible and if it is deemed feasible. E.g. A proposal for nuclear fission might be theoretically possible, but it doesn’t look very feasible in the context of Deep Funding. Viability (secondary) This category is somewhat similar to Feasibility, but it interprets the feasibility against factors such as the size and experience of the team, the budget requested, and the estimated timelines. We could frame this as: “What is your level of confidence that this team will be able to complete this project and its milestones in a reasonable time, and successfully deploy it?” Examples:

A proposal that promises the development of a personal assistant that outperforms existing solutions might be feasible, but if there is no AI expertise in the team the viability rating might be low.
A proposal that promises a new Carbon Emission Compensation scheme might be technically feasible, but the viability could be estimated low due to challenges around market penetration and widespread adoption.

Desirability (secondary) Even if the project team succeeds in creating a product, there is the question of market fit. Is this a project that fulfills an actual need? Is there a lot of competition already? Are the USPs of the project sufficient to make a difference? Example:

Creating a translation service from, say Spanish to English might be possible, but it\'s questionable if such a service would be able to get a significant share of the market

Usefulness (secondary) This is a crucial category that aligns with the main goal of the Deep Funding program. The question to be asked here is: “To what extent will this proposal help to grow the Decentralized AI Platform?” For proposals that develop or utilize an AI service on the platform, the question could be “How many API calls do we expect it to generate” (and how important / high-valued are these calls?). For a marketing proposal, the question could be “How large and well-aligned is the target audience?” Another question is related to how the budget is spent. Are the funds mainly used for value creation for the platform or on other things? Examples:

A metaverse project that spends 95% of its budget on the development of the game and only 5 % on the development of an AI service for the platform might expect a low ‘usefulness’ rating here.

A marketing proposal that creates t-shirts for a local high school, would get a lower ‘usefulness’ rating than a marketing proposal that has a viable plan for targeting highly esteemed universities in a scaleable way.
An AI service that is fully dedicated to a single product, does not take advantage of the purpose of the platform. When the same service would be offered and useful for other parties, this should increase the ‘usefulness’ rating.

Musonda Bemba

Project Owner

Key strengths include: * Transferable skills in AI, logic programming, and neural networks. * Collaborative mindset and ability to work within the PRIMUS ecosystem.

View Profile