DenseShift: Towards Accurate and Efficient Low-Bit Power-of-Two Quantization

1 code implementation • ICCV 2023 • Xinlin Li, Bang Liu, Rui Heng Yang, Vanessa Courville, Chao Xing, Vahid Partovi Nia

We further propose a sign-scale decomposition design to enhance training efficiency and a low-variance random initialization strategy to improve the model's transfer learning performance.

Quantization Transfer Learning

Low-bit Shift Network for End-to-End Spoken Language Understanding

no code implementations • 15 Jul 2022 • Anderson R. Avila, Khalil Bibi, Rui Heng Yang, Xinlin Li, Chao Xing, Xiao Chen

Deep neural networks (DNN) have achieved impressive success in multiple domains.

Edge-computing Quantization +1

Tensor train decompositions on recurrent networks

no code implementations • 9 Jun 2020 • Alejandro Murua, Ramchalam Ramakrishnan, Xinlin Li, Rui Heng Yang, Vahid Partovi Nia

Recurrent neural networks (RNN) such as long-short-term memory (LSTM) networks are essential in a multitude of daily live tasks such as speech, language, video, and multimodal learning.