AI RESEARCH
Two-Valued Symmetric Circulant Matrices: Applications in Deep Learning
arXiv CS.LG
•
ArXi:2605.16443v1 Announce Type: new Despite the success of deep neural networks in vision, medical diagnosis, and IoT scenarios, their deployment on resource-limited platforms poses serious challenges due to their high storage requirements, computational complexity, and large footprint. In particular, fully connected layers require a large number of weights, making it difficult for edge devices to accommodate them.