Search Results for author:
Found 7 papers, 2 papers with code
Temporal Decisions: Leveraging Temporal Correlation for Efficient Decisions in Early Exit Neural Networks
These findings highlight the importance of considering temporal correlation in sensor data to improve the termination decision.
Efficient Post-Training Augmentation for Adaptive Inference in Heterogeneous and Distributed IoT Environments
For an ECG classification task, it was able to terminate all samples early, reducing the mean inference energy by 74. 9% and computations by 78. 3%.
Temporal Patience: Efficient Adaptive Deep Learning for Embedded Radar Data Processing
Radar sensors offer power-efficient solutions for always-on smart devices, but processing the data streams on resource-constrained embedded platforms remains challenging.
Convolutional Neural Networks Quantization with Attention
It has been proven that, compared to using 32-bit floating-point numbers in the training phase, Deep Convolutional Neural Networks (DCNNs) can operate with low precision during inference, thereby saving memory space and power consumption.
Combining Gradients and Probabilities for Heterogeneous Approximation of Neural Networks
We further demonstrate that our error model can predict the parameters of an approximate multiplier in the context of the commonly used additive Gaussian noise (AGN) model with high accuracy.
Compiler Toolchains for Deep Learning Workloads on Embedded Platforms
As the usage of deep learning becomes increasingly popular in mobile and embedded solutions, it is necessary to convert the framework-specific network representations into executable code for these embedded platforms.
Small-Footprint Keyword Spotting on Raw Audio Data with Sinc-Convolutions
Keyword Spotting (KWS) enables speech-based user interaction on smart devices.
