Search Results - "Hu Yuhuang"

Conversion of Continuous-Valued Deep Networks to Efficient Event-Driven Networks for Image Classification by Rueckauer, Bodo, Lungu, Iulia-Alexandra, Hu, Yuhuang, Pfeiffer, Michael, Liu, Shih-Chii

“…neural networks (SNNs) can potentially offer an efficient way of doing inference because the neurons in the networks are sparsely activated and computations…”
Get full text

DVS Benchmark Datasets for Object Tracking, Action Recognition, and Object Recognition by Hu, Yuhuang, Liu, Hongjie, Pfeiffer, Michael, Delbruck, Tobi

“…The first labeled and published event-based neuromorphic vision sensor benchmarks were created from the MNIST digit recognition dataset by jiggling the image…”
Get full text

A Generalized Quantum-Inspired Decision Making Model for Intelligent Agent by Hu, Yuhuang, Loo, Chu Kiong

“…A novel decision making for intelligent agent using quantum-inspired approach is proposed. A formal, generalized solution to the problem is given…”
Get full text

Exploiting Spatial Sparsity for Event Cameras with Visual Transformers by Wang, Zuowen, Hu, Yuhuang, Liu, Shih-Chii

“…Event cameras report local changes of brightness through an asynchronous stream of output events. Events are spatially sparse at pixel locations with little…”
Get full text

v2e: From Video Frames to Realistic DVS Events by Hu, Yuhuang, Liu, Shih-Chii, Delbruck, Tobi

“…To help meet the increasing need for dynamic vision sensor (DVS) event camera data, this paper proposes the v2e toolbox that generates realistic synthetic DVS…”
Get full text

Siamese Networks for Few-Shot Learning on Edge Embedded Devices by Lungu, Iulia Alexandra, Aimar, Alessandro, Hu, Yuhuang, Delbruck, Tobi, Liu, Shih-Chii

“…Edge artificial intelligence hardware targets mainly inference networks that have been pretrained on massive datasets. The field of few-shot learning looks for…”
Get full text

T-NGA: Temporal Network Grafting Algorithm for Learning to Process Spiking Audio Sensor Events by Wang, Shu, Hu, Yuhuang, Liu, Shih-Chii

“…Spiking silicon cochlea sensors encode sound as an asynchronous stream of spikes from different frequency channels. The lack of labeled training datasets for…”
Get full text

Kernel Modulation: A Parameter-Efficient Method for Training Convolutional Neural Networks by Hu, Yuhuang, Liu, Shih-Chii

“…Deep Neural Networks, particularly Convolutional Neural Networks (ConvNets), have achieved incredible success in many vision tasks, but they usually require…”
Get full text

Multiple sequence behavior recognition on humanoid robot using long short-term memory (LSTM) by How, Dickson Neoh Tze, Sahari, Khairul Salleh Mohamed, Hu Yuhuang, Loo Chu Kiong

“…Recurrent neural networks (RNN) are powerful sequence learners. However, RNN suffers from the problem of vanishing gradient point. This fact makes learning…”
Get full text

End-to-End Prediction of Sodium Concentration from Uncalibrated Sodium ISFETs by Wang, Shu, Rovira, Meritxell, Hu, Yuhuang, Jimenez-Jorquera, Cecilia, Liu, Shih-Chii

“…Ion-selective field-effect transistors (ISFETs) are widely used for chemical sensing in biomedical and environmental applications. They require calibration…”
Get full text

Incremental Learning Meets Reduced Precision Networks by Hu, Yuhuang, Delbruck, Tobi, Liu, Shih-Chii

“…Hardware accelerators for Deep Neural Networks (DNNs) that use reduced precision parameters are more energy efficient than the equivalent full precision…”
Get full text

Learning sufficient representation for spatio-temporal deep network using information filter by Yuhuang Hu, Neoh, Dickson Tze How, Sahari, Khairul Salleh Mohamed, Chu Kiong Loo

“…This article introduced an improved spatio - temporal deep network based on information filter method for learning sufficient representation. The proposed…”
Get full text

Kernel Modulation: A Parameter-Efficient Method for Training Convolutional Neural Networks by Hu, Yuhuang, Liu, Shih-Chii

“…Deep Neural Networks, particularly Convolutional Neural Networks (ConvNets), have achieved incredible success in many vision tasks, but they usually require…”
Get full text

DDD20 End-to-End Event Camera Driving Dataset: Fusing Frames and Events with Deep Learning for Improved Steering Prediction by Hu, Yuhuang, Binas, Jonathan, Neil, Daniel, Liu, Shih-Chii, Delbruck, Tobi

“…Neuromorphic event cameras are useful for dynamic vision problems under difficult lighting conditions. To enable studies of using event cameras in automobile…”
Get full text

Exploiting Spatial Sparsity for Event Cameras with Visual Transformers by Wang, Zuowen, Hu, Yuhuang, Liu, Shih-Chii

“…Event cameras report local changes of brightness through an asynchronous stream of output events. Events are spatially sparse at pixel locations with little…”
Get full text

T-NGA: Temporal Network Grafting Algorithm for Learning to Process Spiking Audio Sensor Events by Wang, Shu, Hu, Yuhuang, Liu, Shih-Chii

“…Spiking silicon cochlea sensors encode sound as an asynchronous stream of spikes from different frequency channels. The lack of labeled training datasets for…”
Get full text

v2e: From Video Frames to Realistic DVS Events by Hu, Yuhuang, Liu, Shih-Chii, Delbruck, Tobi

“…To help meet the increasing need for dynamic vision sensor (DVS) event camera data, this paper proposes the v2e toolbox that generates realistic synthetic DVS…”
Get full text

Learning to Exploit Multiple Vision Modalities by Using Grafted Networks by Hu, Yuhuang, Delbruck, Tobi, Liu, Shih-Chii

“…Novel vision sensors such as thermal, hyperspectral, polarization, and event cameras provide information that is not available from conventional intensity…”
Get full text

Slasher: Stadium racer car for event camera end-to-end learning autonomous driving experiments by Hu, Yuhuang, Chen, Hong Ming, Delbruck, Tobi

“…Slasher is the first open 1/10 scale autonomous driving platform for exploring the use of neuromorphic event cameras for fast driving in unstructured indoor…”
Get full text

Prediction of Gas Concentration Using Gated Recurrent Neural Networks by Wang, Shu, Hu, Yuhuang, Burgues, Javier, Marco, Santiago, Liu, Shih-Chii

“…Low-cost gas sensors allow for large-scale spatial monitoring of air quality in the environment. However they require calibration before deployment. Methods…”
Get full text