Abstract: Low bit-precisions and their bit-slice sparsity have recently been studied to accelerate general matrix-multiplications (GEMM) during large-scale deep neural network (DNN) inferences. While ...
Abstract: We present a monolithically integrated, fully reconfigurable photonic analogtodigital converter (ADC) that implements signal quantization weighting in the optical domain. By dynamically ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results