Imperial College London > Talks@ee.imperial > CAS Talks > Memory-aware dynamic spatially adaptive inference
Log inImperial users Other users No account?Information onFinding a talk Adding a talk Syndicating talks Who we are Everything else |
Memory-aware dynamic spatially adaptive inferenceAdd to your list(s) Download to your calendar using vCal
If you have a question about this talk, please contact George A Constantinides. In dynamic systems, the ability to adapt to varying computational costs is useful, since computational resources can fluctuate in real-time, therefore operating across a spectrum of FLOP budgets is an important advantage for deep learning models. Moreover, with real systems constrained by finite memory capacities, it becomes imperative to account for this limitation in model design. This talk aims to explore the multifaceted challenges inherent in balancing performance against FLO Ps and the number of parameters. Finally, leveraging the effectiveness of spatially adaptive methods in achieving favorable performance to computational cost trade-offs, a multi-target training scheme is proposed to achieve dynamic inference with negligible parameter number increase. This talk is part of the CAS Talks series. This talk is included in these lists:
Note that ex-directory lists are not shown. |
Other listsMastering the Art of Shopping: Your Ultimate Guide to Finding the Best Deals Cardiff Podiatry - Confident Walk and Healthy Feet SW BeautyBar Zürich: Botulinumtoxin (Botox®), Filler, Lips, BrowsOther talksDifferential Linear Matrix Inequalities Getting the best out of life Keynote Speech on Influence and persuasion Control of Uncertainty or Control with Uncertainty? A New Control Design Paradigm for Autonomous Stochastic Systems |