Sustainable AI: Mathematical Foundations of Spiking Neural Networks
Deep learning's success comes with growing energy demands, raising concerns about the long-term sustainability of the field. Spiking neural networks, inspired by biological neurons, offer a promising alternative with potential computational and energy-efficiency gains. This article examines the computational properties of spiking networks through the lens of learning theory, focusing on expressivity, training, and generalization, as well as energy-efficient implementations while comparing them to artificial neural networks. By categorizing spiking models based on time representation and information encoding, we highlight their strengths, challenges, and potential as an alternative computational paradigm.
Code (0)
등록된 구현이 없습니다.
Tasks
Learning TheorySimilar Papers 제목 키워드 기반
Interdisciplinary Business Games on Sustainable Development: Theoretical Foundations and Prospects of Implementation
The article defines the place of business games among all games in general based on the classification by F.G. Junger; it provides critical analysis of existing business games types; it also formulates requirements and l…
Material Measurement Units for a Circular Economy: Foundations through a Review
Long-term availability of minerals and industrial materials is a necessary condition for sustainable development as they are the constituents of any manufacturing product. To enhance the efficiency of material management…
ManagementMathematical Foundations of Geometric Deep Learning
We review the key mathematical concepts necessary for studying Geometric Deep Learning.
Distribution-Aware Compensation Design for Sustainable Data Rights in Machine Learning
Modern distributed learning systems face a critical challenge when clients request the removal of their data influence from trained models, as this process can significantly destabilize system performance and affect rema…
Decision MakingDiversityEfficient Aspect Term Extraction using Spiking Neural Network
Aspect Term Extraction (ATE) identifies aspect terms in review sentences, a key subtask of sentiment analysis. While most existing approaches use energy-intensive deep neural networks (DNNs) for ATE as sequence labeling,…
Sentiment AnalysisTerm Extraction