Distributed B-SDLM: accelerating the training convergence of deep neural networks through parallelism
This paper proposes an efficient asynchronous stochastic second order learning algorithm for distributed learning of neural networks (NNs). The proposed algorithm, named distributed bounded stochastic diagonal Levenberg-Marquardt (distributed B-SDLM), is based on the B-SDLM algorithm that converges...
à®®à¯à®´à¯ விளகà¯à®•à®®à¯
Saved in:
| தலைமை எழà¯à®¤à¯à®¤à®¾à®³à®°à¯à®•ளà¯: | , , |
|---|---|
| வடிவமà¯: | Conference or Workshop Item |
| வெளியீடபà¯à®ªà®Ÿà¯à®Ÿà®¤à¯: |
Springer Verlag
2016
|
| பகà¯à®¤à®¿à®•ளà¯: | |
| நிகழà¯à®¨à®¿à®²à¯ˆ அணà¯à®•லà¯: | http://eprints.utm.my/73608/ http://eprints.utm.my/73608/ |
| கà¯à®±à®¿à®¯à¯€à®Ÿà¯à®•ளà¯: |
கà¯à®±à®¿à®šà¯à®šà¯Šà®²à¯ இணை
கà¯à®±à®¿à®¯à¯€à®Ÿà¯à®•ள௠இலà¯à®²à¯ˆ, இநà¯à®¤ கà¯à®±à®¿à®šà¯à®šà¯Šà®²à¯à®²à¯ˆ à®®à¯à®¤à®²à®¿à®²à¯ பதிவ௠செயà¯à®¯à¯à®™à¯à®•ளà¯!
|