Speedup deep learning models on GPU by taking advantage of efficient unstructured pruning and bit-width reduction
Marcin Pietroń, Dominik Żurek, Bartłomiej Śnieżyński
Topics & Concepts
Computer sciencePruningSpeedupConvolutional neural networkDeep learningMemory footprintFLOPSReduction (mathematics)Artificial intelligenceParallel computingArtificial neural networkCUDAAlgorithmMathematicsGeometryAgronomyOperating systemBiologyAdvanced Neural Network ApplicationsMachine Learning and ELMDomain Adaptation and Few-Shot Learning