dcmocanu/sparse-evolutionary-artificial-neural-networks
Always sparse. Never dense. But never say never. A Sparse Training repository for the Adaptive Sparse Connectivity concept and its algorithmic instantiation, i.e. Sparse Evolutionary Training, to boost Deep Learning scalability on various aspects (e.g. memory and computational time efficiency, representation and generalization power).
PythonMIT
Stargazers
- 227332The Netherlands
- abhesrivas
- AlexandruBurlacuChisinau, Republic of Moldova
- auzahetaETH Zürich
- blidarescubRomania
- claudioscheerBrazil
- clungztaTraversal Labs
- davidsteinar
- Digestivee
- elranu@randlabs
- emerali@PIQuIL
- fgsilva
- gianluvillani
- jeroenvlekPerceptive Bits
- kduy
- kebitmatfSouth of Korea
- kneehitComputer Vision Engineer @ Jabra
- latticetower@kalininalab
- MehdiAbbanaBennaniRIKEN
- MElHuseyniG2K
- nagpaulMontreal
- nareshshah139Untangle AI
- nickvazzTau Motors
- NVFXNVIDIA
- rahul1906Lemnisk
- RameshOswal
- rbarghouUnited States
- rileytwoKansas City, Missouri
- ritchie46Utrecht
- shak360Oakland, California
- timhartillNeuralition
- tudorsabin
- vlukiyanovLondon
- wlongxiangAmsterdam
- xkey-
- yutarochan@IBMResearch