arXiv:1711.06935
Interleaver Design for Deep Neural Networks
원문 초록
We propose a class of interleavers for a novel deep neural network (DNN) architecture that uses algorithmically pre-determined, structured sparsity to significantly lower memory and computational requirements, and speed up training. The interleavers guarantee clash-free memory accesses to eliminate idle operational cycles, optimize spread and dispersion to improve network performance, and are designed to ease the complexity of memory address computations in hardware. We present a design algorithm with mathematical proofs for these properties. We also explore interleaver variations and analyze the behavior of neural networks as a function of interleaver metrics.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
StepProof: Step-by-step verification of natural language mathematical proofs
A Theoretical Analysis of Compositional Generalization in Neural Networks: A Necessary and Sufficient Condition
Hierarchical Attention Generates Better Proofs
Distance-Adaptive Quaternion Knowledge Graph Embedding with Bidirectional Rotation
Learning Rules Explaining Interactive Theorem Proving Tactic Prediction
ODGS: 3D Scene Reconstruction from Omnidirectional Images with 3D Gaussian Splattings
토론
이 논문과 연결된 포럼 글이 아직 없습니다.