Abstract: A fast analysis method for large finite arrays is proposed, which directly employs the near-field Huygens surface data of an isolated element instead of its full structural model. By ...
Abstract: On-device fixed-point deep neural network (DNN) accelerators are widely used, but the multiply-accumulate (MAC) units that perform the atomic operations in DNNs have become inefficient due ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results