NeuroBlend: Towards Low-Power yet Accurate Neural Network-Based Inference Engine Blending Binary and Fixed-Point Convolutions
Open Access
- 12 June 2024
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 730-735
Abstract
No abstract availableAll Related Versions
Funding Information
- National Science Foundation
This publication has 15 references indexed in Scilit:
- PresB-Net: parametric binarized neural network with learnable activations and shuffled grouped convolutionPeerJ Computer Science, 2022
- Gradient Matters: Designing Binarized Neural Networks via Enhanced Information-FlowIEEE Transactions on Pattern Analysis and Machine Intelligence, 2021
- Swin Transformer: Hierarchical Vision Transformer using Shifted Windows2021
- AresB-Net: accurate residual binarized neural networks using shortcut concatenation and shuffled grouped convolutionPeerJ Computer Science, 2021
- FracBNN: Accurate and FPGA-Efficient Binary Neural Networks with Fractional Activations2021
- ReActNet: Towards Precise Binary Neural Network with Generalized Activation Functions2020
- Bi-Real Net: Enhancing the Performance of 1-Bit CNNs with Improved Representational Capability and Advanced Training Algorithm2018
- MobileNetV2: Inverted Residuals and Linear Bottlenecks2018
- FINN2017
- XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks2016