Saved in:
| Main Author: | |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2506.12111 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908407731060736 |
|---|---|
| author | Dapena, Oscar Boullosa |
| author_facet | Dapena, Oscar Boullosa |
| contents | Real-time continuous learning over streaming data remains a central challenge in deep learning and AI systems. Traditional gradient-based models such as backpropagation through time (BPTT) face computational and stability limitations when dealing with temporally unbounded data. In this paper, we introduce a novel architecture, Quantum-Inspired Differentiable Integral Neural Networks (QIDINNs), which leverages the Feynman technique of differentiation under the integral sign to formulate neural updates as integrals over historical data. This reformulation allows for smoother, more stable learning dynamics that are both physically interpretable and computationally tractable. Inspired by Feynman's path integral formalism and compatible with quantum gradient estimation frameworks, QIDINNs open a path toward hybrid classical-quantum neural computation. We demonstrate our model's effectiveness on synthetic and real-world streaming tasks, and we propose directions for quantum extensions and scalable implementations. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_12111 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Quantum-Inspired Differentiable Integral Neural Networks (QIDINNs): A Feynman-Based Architecture for Continuous Learning Over Streaming Data Dapena, Oscar Boullosa Software Engineering Artificial Intelligence Computation and Language Machine Learning Real-time continuous learning over streaming data remains a central challenge in deep learning and AI systems. Traditional gradient-based models such as backpropagation through time (BPTT) face computational and stability limitations when dealing with temporally unbounded data. In this paper, we introduce a novel architecture, Quantum-Inspired Differentiable Integral Neural Networks (QIDINNs), which leverages the Feynman technique of differentiation under the integral sign to formulate neural updates as integrals over historical data. This reformulation allows for smoother, more stable learning dynamics that are both physically interpretable and computationally tractable. Inspired by Feynman's path integral formalism and compatible with quantum gradient estimation frameworks, QIDINNs open a path toward hybrid classical-quantum neural computation. We demonstrate our model's effectiveness on synthetic and real-world streaming tasks, and we propose directions for quantum extensions and scalable implementations. |
| title | Quantum-Inspired Differentiable Integral Neural Networks (QIDINNs): A Feynman-Based Architecture for Continuous Learning Over Streaming Data |
| topic | Software Engineering Artificial Intelligence Computation and Language Machine Learning |
| url | https://arxiv.org/abs/2506.12111 |