P
Pierce I.Jen Chuang
Researcher at IBM
Publications - 4
Citations - 712
Pierce I.Jen Chuang is an academic researcher from IBM. The author has contributed to research in topics: Quantization (signal processing) & Computer science. The author has an hindex of 2, co-authored 2 publications receiving 474 citations.
Papers
More filters
Posted Content
PACT: Parameterized Clipping Activation for Quantized Neural Networks
Jungwook Choi,Zhuo Wang,Swagath Venkataramani,Pierce I.Jen Chuang,Vijayalakshmi Srinivasan,Kailash Gopalakrishnan +5 more
TL;DR: It is shown, for the first time, that both weights and activations can be quantized to 4-bits of precision while still achieving accuracy comparable to full precision networks across a range of popular models and datasets.
Posted Content
Bridging the accuracy gap for 2-bit Quantized Neural Networks (QNN)
Jungwook Choi,Pierce I.Jen Chuang,Zhuo Wang,Zhuo Wang,Swagath Venkataramani,Vijayalakshmi Srinivasan,Kailash Gopalakrishnan +6 more
TL;DR: This paper proposes novel techniques that target weight and activation quantizations separately resulting in an overall quantized neural network (QNN) that achieves state-of-the-art classification accuracy across a range of popular models and datasets.
Journal ArticleDOI
Now It Sounds Like You: Learning Personalized Vocabulary On Device
TL;DR: This article proposed a novel technique called "OOV expansion" that improves OOV coverage and increases model accuracy while minimizing the impact on memory and latency, which significantly outperforms standard FL personalization methods on a set of common FL benchmarks.
Proceedings Article
Towards Zero-Shot Multilingual Transfer for Code-Switched Responses
Ting-Wei Wu,Changsheng Zhao,Ernie Chang,Yangyang Shi,Pierce I.Jen Chuang,Vikas Chandra,Biing-Hwang Juang +6 more
TL;DR: The authors investigate the use of state-of-the-art multilingual models such as mBART and T5 to facilitate zero-shot and few-shot transfer of code-switched responses.