Optimized injection of noise in activation functions to improve generalization of neural networks

Duan, Fabing; Chapeau-Blondeau, François; Abbott, Derek

doi:10.1016/j.chaos.2023.114363

Chaos, Solitons & Fractals

2024

DOI: 10.1016/j.chaos.2023.114363

|View full text |Cite

Optimized injection of noise in activation functions to improve generalization of neural networks

Fabing Duan,

François Chapeau-Blondeau,

Derek Abbott

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...

Citation Types

Supporting

Mentioning

Contrasting

Year Published

2024

Publication Types

Select...

Article1

Relationship

Self Cite0

Independent1

Authors

Journals

Cited by 1 publication

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

Topologically Defective Lattice Potential‐Based Gain‐Dissipative Ising Annealer with Large Noise Margin

Liao,

Tang,

Sarker

et al. 2024

Advanced Physics Research

View full text Add to dashboard Cite

Gain‐dissipative Ising machines (GIMs) are annealers inspired by physical systems such as Ising spin glasses to solve combinatorial optimization problems. Compared to traditional quantum annealers, GIM is relatively easier to scale and can save on additional power consumption caused by low‐temperature cooling. However, traditional GIMs have a limited noise margin. Specifically, their normal operation requires ensuring that the noise intensity is lower than their saturation fixed point amplitude, which may result in increased power consumption to suppress noise‐induced spin state switching. To enhance the noise robustness of GIM, in this study a GIM based on a topologically defective lattice potential (TDLP) is proposed. Numerical simulations demonstrate that the TDLP‐based GIM can accurately simulate the bifurcation spin evolution in the Ising model. Furthermore, through the MAXCUT benchmark based on G‐set graphs, the optimal performance of TDLP‐based GIM is shown to surpass that of traditional GIMs. Additionally, the proposed TDLP‐based GIM successfully solves the MAXCUT benchmark and domain clustering dynamics benchmark based on G‐set graphs when the noise intensity exceeds its saturation fixed‐point amplitude. This indicates that the proposed system provides a promising architecture for breaking the small noise constraints required by traditional GIMs.

show abstract

Topologically Defective Lattice Potential‐Based Gain‐Dissipative Ising Annealer with Large Noise Margin

Liao,

Tang,

Sarker

et al. 2024

Advanced Physics Research

View full text Add to dashboard Cite

show abstract

scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.

Contact Info

hi@scite.ai

10624 S. Eastern Ave., Ste. A-614

Henderson, NV 89052, USA

Blog Terms and Conditions API Terms Privacy Policy Contact Cookie Preferences Do Not Sell or Share My Personal Information

Made with 💙 for researchers

Part of the Research Solutions Family.

Optimized injection of noise in activation functions to improve generalization of neural networks

Cited by 1 publication

References 37 publications

Topologically Defective Lattice Potential‐Based Gain‐Dissipative Ising Annealer with Large Noise Margin

Topologically Defective Lattice Potential‐Based Gain‐Dissipative Ising Annealer with Large Noise Margin

Contact Info

Product

Resources

About