MixedNet: Network Design Strategies for Cost-Effective Quantized CNNs
This paper proposes design strategies for a low-cost quantized neural network. To prevent the classification accuracy from being degraded by quantization, a structure-design strategy that utilizes a large number of channels rather than deep layers is proposed. In addition, a squeeze-and-excitation (...
Main Authors: | Dong-Jin Chang, Byeong-Gyu Nam, Seung-Tak Ryu |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2021-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/9520426/ |
Similar Items
-
Spatial Shift Point-Wise Quantization
by: Eunhui Kim, et al.
Published: (2020-01-01) -
Optimizing Spatial Shift Point-Wise Quantization
by: Eunhui Kim, et al.
Published: (2021-01-01) -
NAND Flash Based Novel Synaptic Architecture for Highly Robust and High-Density Quantized Neural Networks With Binary Neuron Activation of (1, 0)
by: Sung-Tae Lee, et al.
Published: (2020-01-01) -
Recent Progress on Memristive Convolutional Neural Networks for Edge Intelligence
by: Yi-Fan Qin, et al.
Published: (2020-11-01) -
Accelerating Inference of Convolutional Neural Networks Using In-memory Computing
by: Martino Dazzi, et al.
Published: (2021-08-01)