3 accepted papers
"Quantization is a very effective optimization technique to reduce hardware cost and memory footprint of deep neural network (DNN) accelerators. In particular, post-training quantization (PTQ) is often preferred as it does not require a full dataset or costly retraining. However, performance of PTQ…
Quantization plays an important role in deep neural network (DNN) hardware. In particular, logarithmic quantization has multiple advantages for DNN hardware implementations, and its weakness in terms of lower performance at high precision compared with linear quantization has been recently remedied…
The CaseCrawler is a lightweight and low-profile movable platform with a high payload capacity; it is capable of crawling around carrying a smartphone. The body of the robot resembles a phone case but it has crawling legs stored in its back. It is designed with a deployable, in-plane transmission th