no code implementations • 29 Mar 2022 • Yuhuang Hu, Shih-Chii Liu
This work proposes a novel parameter-efficient kernel modulation (KM) method that adapts all parameters of a base network instead of a subset of layers.
no code implementations • 10 Feb 2022 • Zuowen Wang, Yuhuang Hu, Shih-Chii Liu
The input to the ViT consists of events that are accumulated into time bins and spatially separated into non-overlapping sub-regions called patches.
no code implementations • 7 Feb 2022 • Shu Wang, Yuhuang Hu, Shih-Chii Liu
This work proposes a self-supervised method called Temporal Network Grafting Algorithm (T-NGA), which grafts a recurrent network pretrained on spectrogram features so that the network works with the cochlea event features.
3 code implementations • 13 Jun 2020 • Yuhuang Hu, Shih-Chii Liu, Tobi Delbruck
The first experiment is object recognition with N-Caltech 101 dataset.
1 code implementation • 18 May 2020 • Yuhuang Hu, Jonathan Binas, Daniel Neil, Shih-Chii Liu, Tobi Delbruck
The dataset was captured with a DAVIS camera that concurrently streams both dynamic vision sensor (DVS) brightness change events and active pixel sensor (APS) intensity frames.
no code implementations • ACL 2020 • Yingqiang Gao, Nikola I. Nikolov, Yuhuang Hu, Richard H. R. Hahnloser
We explore the suitability of self-attention models for character-level neural machine translation.
no code implementations • ECCV 2020 • Yuhuang Hu, Tobi Delbruck, Shih-Chii Liu
This paper proposes a Network Grafting Algorithm (NGA), where a new front end network driven by unconventional visual inputs replaces the front end network of a pretrained deep network that processes intensity frames.
Ranked #4 on Event-based Object Segmentation on RGBE-SEG
1 code implementation • WS 2018 • Nikola I. Nikolov, Yuhuang Hu, Mi Xue Tan, Richard H. R. Hahnloser
Character-level Neural Machine Translation (NMT) models have recently achieved impressive results on many language pairs.
no code implementations • ICLR 2018 • Yuhuang Hu, Adrian Huber, Jithendar Anumula, Shih-Chii Liu
Plain recurrent networks greatly suffer from the vanishing gradient problem while Gated Neural Networks (GNNs) such as Long-short Term Memory (LSTM) and Gated Recurrent Unit (GRU) deliver promising results in many sequence learning tasks through sophisticated network designs.
no code implementations • 13 Dec 2016 • Bodo Rueckauer, Iulia-Alexandra Lungu, Yuhuang Hu, Michael Pfeiffer
Deep convolutional neural networks (CNNs) have shown great potential for numerous real-world machine learning applications, but performing inference in large CNNs in real-time remains a challenge.
no code implementations • 2 Jun 2015 • Yuhuang Hu, M. S. Ishwarya, Chu Kiong Loo
This article demonstrates a new conceptor network based classifier in classifying images.