Picture for Steve Wilton

Steve Wilton

ZOBNN: Zero-Overhead Dependable Design of Binary Neural Networks with Deliberately Quantized Parameters

Add code
Jul 06, 2024
Viaarxiv icon

QUTE: Quantifying Uncertainty in TinyML models with Early-exit-assisted ensembles

Add code
Apr 19, 2024
Figure 1 for QUTE: Quantifying Uncertainty in TinyML models with Early-exit-assisted ensembles
Figure 2 for QUTE: Quantifying Uncertainty in TinyML models with Early-exit-assisted ensembles
Figure 3 for QUTE: Quantifying Uncertainty in TinyML models with Early-exit-assisted ensembles
Figure 4 for QUTE: Quantifying Uncertainty in TinyML models with Early-exit-assisted ensembles
Viaarxiv icon

DNN Memory Footprint Reduction via Post-Training Intra-Layer Multi-Precision Quantization

Add code
Apr 03, 2024
Viaarxiv icon

T-RECX: Tiny-Resource Efficient Convolutional Neural Networks with Early-Exit

Add code
Jul 14, 2022
Figure 1 for T-RECX: Tiny-Resource Efficient Convolutional Neural Networks with Early-Exit
Figure 2 for T-RECX: Tiny-Resource Efficient Convolutional Neural Networks with Early-Exit
Figure 3 for T-RECX: Tiny-Resource Efficient Convolutional Neural Networks with Early-Exit
Figure 4 for T-RECX: Tiny-Resource Efficient Convolutional Neural Networks with Early-Exit
Viaarxiv icon

MAFIA: Machine Learning Acceleration on FPGAs for IoT Applications

Add code
Jul 08, 2021
Figure 1 for MAFIA: Machine Learning Acceleration on FPGAs for IoT Applications
Figure 2 for MAFIA: Machine Learning Acceleration on FPGAs for IoT Applications
Figure 3 for MAFIA: Machine Learning Acceleration on FPGAs for IoT Applications
Figure 4 for MAFIA: Machine Learning Acceleration on FPGAs for IoT Applications
Viaarxiv icon