LIU Weichen

Appointment: Nanyang Assistant Professor

Research topics:
• Embedded and Real-Time Systems
• Many-Core Systems
• Electronic/Photonic Network-on-Chip
• Machine Learning Acceleration
• Computer Architecture

Featured Dataverses

In order to use this feature you must have at least one published dataverse.

Publish Dataverse

Are you sure you want to publish your dataverse? Once you do so it must remain published.

Publish Dataverse

This dataverse cannot be published because the dataverse it is in has not been published.

Delete Dataverse

Are you sure you want to delete your dataverse? You cannot undelete this dataverse.

1,011 to 1,020 of 1,021 Results

trans_vgg19.py Mar 7, 2022 - ZeroBN: Learning Compact Neural Networks For Latency-Critical Edge Systems Python Source Code - 6.8 KB - MD5: 84507eaff9691c96a6a3806dd803924c
vgg.py Mar 7, 2022 - ZeroBN: Learning Compact Neural Networks For Latency-Critical Edge Systems Python Source Code - 3.9 KB - MD5: 9bdf5811eb5fcccc8c14c8edcdfd3bed
vgg.py Mar 7, 2022 - ZeroBN: Learning Compact Neural Networks For Latency-Critical Edge Systems Python Source Code - 2.4 KB - MD5: e03fa18983a2524a824b73f8f4660dda
vgg_torch.py Mar 7, 2022 - ZeroBN: Learning Compact Neural Networks For Latency-Critical Edge Systems Python Source Code - 2.7 KB - MD5: d291dc48bd5a253a62e123af35e3dbc6
y_i.tab Mar 7, 2022 - ZeroBN: Learning Compact Neural Networks For Latency-Critical Edge Systems Tabular Data - 172.0 KB - 1 Variables, 5503 Observations - UNF:6:+jmG0vdNb5kvT4IJ3OJAeA==
Replication Data for: XOR-Net: An Efficient Computation Pipeline for Binary Neural Network Inference on Edge Devices Dec 21, 2020 - Zhu Shien Zhu, Shien; Duong, H. K. Luan; Liu, Weichen, 2020, "Replication Data for: XOR-Net: An Efficient Computation Pipeline for Binary Neural Network Inference on Edge Devices", https://doi.org/10.21979/N9/XEH3D1, DR-NTU (Data), V1, UNF:6:5DOBB66c624HMnkRD7Qw9g== [fileUNF] Accepted as a conference paper by IEEE International Conference on Parallel and Distributed Systems (ICPADS) 2020.
gap8.zip Dec 21, 2020 - Replication Data for: XOR-Net: An Efficient Computation Pipeline for Binary Neural Network Inference on Edge Devices ZIP Archive - 1.2 GB - MD5: ce4fc478984c26ed80a6c83abfb1bd8c Code The_GAP8_SDK that contains the compiler and source codes
ICPADS 2020 XOR-Net Latex.zip Dec 21, 2020 - Replication Data for: XOR-Net: An Efficient Computation Pipeline for Binary Neural Network Inference on Edge Devices ZIP Archive - 2.0 MB - MD5: 851043007b84fd2c2599ebd2485c71e1 Documentation The latex folder of the paper
ICPADS_2020_XOR-Net_PPT.pdf Dec 21, 2020 - Replication Data for: XOR-Net: An Efficient Computation Pipeline for Binary Neural Network Inference on Edge Devices Adobe PDF - 2.3 MB - MD5: 4a934600b747084740524d91df1c1909 Documentation The PPT for the conference
XOR-Net Performance Summary 2020-7-22.tab Dec 21, 2020 - Replication Data for: XOR-Net: An Efficient Computation Pipeline for Binary Neural Network Inference on Edge Devices Tabular Data - 19.2 KB - 17 Variables, 149 Observations - UNF:6:VrCPbjap40q9aQlCjvdQBA== Data The performance of XOR-Net and competing methods.

trans_vgg19.py

Mar 7, 2022 - ZeroBN: Learning Compact Neural Networks For Latency-Critical Edge Systems

Python Source Code - 6.8 KB -

vgg.py

Mar 7, 2022 - ZeroBN: Learning Compact Neural Networks For Latency-Critical Edge Systems

Python Source Code - 3.9 KB -

vgg.py

Mar 7, 2022 - ZeroBN: Learning Compact Neural Networks For Latency-Critical Edge Systems

Python Source Code - 2.4 KB -

vgg_torch.py

Mar 7, 2022 - ZeroBN: Learning Compact Neural Networks For Latency-Critical Edge Systems

Python Source Code - 2.7 KB -

y_i.tab

Mar 7, 2022 - ZeroBN: Learning Compact Neural Networks For Latency-Critical Edge Systems

Tabular Data - 172.0 KB - 1 Variables, 5503 Observations -

Replication Data for: XOR-Net: An Efficient Computation Pipeline for Binary Neural Network Inference on Edge Devices

Dec 21, 2020 - Zhu Shien

Zhu, Shien; Duong, H. K. Luan; Liu, Weichen, 2020, "Replication Data for: XOR-Net: An Efficient Computation Pipeline for Binary Neural Network Inference on Edge Devices", https://doi.org/10.21979/N9/XEH3D1, DR-NTU (Data), V1, UNF:6:5DOBB66c624HMnkRD7Qw9g== [fileUNF]

Accepted as a conference paper by IEEE International Conference on Parallel and Distributed Systems (ICPADS) 2020.

gap8.zip

Dec 21, 2020 - Replication Data for: XOR-Net: An Efficient Computation Pipeline for Binary Neural Network Inference on Edge Devices

ZIP Archive - 1.2 GB -

Code

The_GAP8_SDK that contains the compiler and source codes

ICPADS 2020 XOR-Net Latex.zip

Dec 21, 2020 - Replication Data for: XOR-Net: An Efficient Computation Pipeline for Binary Neural Network Inference on Edge Devices

ZIP Archive - 2.0 MB -

Documentation

The latex folder of the paper

ICPADS_2020_XOR-Net_PPT.pdf

Dec 21, 2020 - Replication Data for: XOR-Net: An Efficient Computation Pipeline for Binary Neural Network Inference on Edge Devices

Adobe PDF - 2.3 MB -

Documentation

The PPT for the conference

XOR-Net Performance Summary 2020-7-22.tab

Dec 21, 2020 - Replication Data for: XOR-Net: An Efficient Computation Pipeline for Binary Neural Network Inference on Edge Devices

Tabular Data - 19.2 KB - 17 Variables, 149 Observations -

Data

The performance of XOR-Net and competing methods.

Add Data

Share Dataverse

Link Dataverse

Reset Modifications