Search Results for author:
Found 8 papers, 1 papers with code
Closing the Gap between Client and Global Model Performance in Heterogeneous Federated Learning
The heterogeneity of hardware and data is a well-known and studied problem in the community of Federated Learning (FL) as running under heterogeneous settings.
Data Selection for Efficient Model Update in Federated Learning
Our experiments show that only 1. 6% of the initially exchanged data can effectively transfer the characteristic of the client data to the global model in our FL approach, using split networks.
Optimising the Performance of Convolutional Neural Networks across Computing Systems using Transfer Learning
This process requires a lengthy profiling stage, iterating over all the available primitives for each layer configuration, to measure their execution time on the target platform.
TASO: Time and Space Optimization for Memory-Constrained DNN Inference
We optimize the trade-off between execution time and memory consumption by: 1) attempting to minimize execution time across the whole network by selecting data layouts and primitive operations to implement each layer; and 2) allocating an appropriate workspace that reflects the upper bound of memory footprint per layer.
Performance Aware Convolutional Neural Network Channel Pruning for Embedded GPUs
We evaluate higher level libraries, which analyze the input characteristics of a convolutional layer, based on which they produce optimized OpenCL (Arm Compute Library and TVM) and CUDA (cuDNN) code.
CamLoc: Pedestrian Location Detection from Pose Estimation on Resource-constrained Smart-cameras
Video processing holds utility for many emerging applications and data labelling in the IoT space.
Distilling with Performance Enhanced Students
The task of accelerating large neural networks on general purpose hardware has, in recent years, prompted the use of channel pruning to reduce network size.
Characterising Across-Stack Optimisations for Deep Convolutional Neural Networks
Convolutional Neural Networks (CNNs) are extremely computationally demanding, presenting a large barrier to their deployment on resource-constrained devices.
