What is Pruning?
Zeroing out low-impact weights in a neural network to reduce computation and memory. Structured pruning, which follows fixed patterns, is easier to accelerate in hardware.
Field: AI Hardware & Software Stack
Pruning in the explanations
Pruning zeros out weights with little influence, such as those with small values, to reduce computation and memory.
Which statement about pruning neural networks is correct?It is used alongside quantization and pruning to reduce inference compute and memory.
Which describes knowledge distillation?
Questions that mention Pruning (2)
Related terms
Speedup Knowledge distillation AI compiler AI inference All-reduce Arithmetic intensity Attention mechanism Backpropagation Batch size Computational graph