English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Recent years have seen a paradigm shift towards multi-task learning. Thiscalls for memory and energy-efficient solutions for inference in a multi-taskscenario. We propose an algorithm-hardware co-design approach called MIME. MIMEreuses the weight parameters of a trained parent task and learns task-specificthreshold parameters for inference on multiple child tasks. We find that MIMEresults in highly memory-efficient DRAM storage of neural-network parametersfor multiple tasks compared to conventional multi-task inference. In addition,MIME results in input-dependent dynamic neuronal pruning, thereby enablingenergy-efficient inference with higher throughput on a systolic-array hardware.Our experiments with benchmark datasets (child tasks)- CIFAR10, CIFAR100, andFashion-MNIST, show that MIME achieves ~3.48x memory-efficiency and ~2.4-3.1xenergy-savings compared to conventional multi-task inference in Pipelined taskmode.

MIME: Adapting a Single Neural Network for Multi-task Inference with Memory-efficient Dynamic Pruning