Filters








4 Hits in 2.0 sec

Flambé: A Customizable Framework for Machine Learning Experiments

Jeremy Wohlwend, Nicholas Matthews, Ivan Itzcovich
2019 Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics: System Demonstrations  
Flambé is a machine learning experimentation framework built to accelerate the entire research life cycle.  ...  Flambé's main objective is to provide a unified interface for prototyping models, running experiments containing complex pipelines, monitoring those experiments in real-time, reporting results, and deploying  ...  The Flambé Framework Flambé executes experiments which are composed of a pipeline of modeling and processing stages (Subsection A), extensions that import usersupplied code (Subsection B), links to existing  ... 
doi:10.18653/v1/p19-3029 dblp:conf/acl/WohlwendMI19 fatcat:42bvlor74vbm3pklpcsdueydoa

Autoregressive Knowledge Distillation through Imitation Learning [article]

Alexander Lin, Jeremy Wohlwend, Howard Chen, Tao Lei
2020 arXiv   pre-print
We develop a compression technique for autoregressive models that is driven by an imitation learning perspective on knowledge distillation.  ...  Acknowledgments We thank the ASAPP NLP team -especially Yi Yang, Nicholas Matthews, Joshua Shapiro, Hugh Perkins, Amit Ganatra, Lili Yu, Xinyuan Zhang, and Yoav Artzi -as well as the EMNLP reviewers for  ...  Our experiments were conducted using Flambé, a PyTorch-based model training and evaluation library (Wohlwend et al., 2019) .  ... 
arXiv:2009.07253v2 fatcat:2pk5mt46zjemznssyle2zwxua4

Autoregressive Knowledge Distillation through Imitation Learning

Alexander Lin, Jeremy Wohlwend, Howard Chen, Tao Lei
2020 Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)   unpublished
We develop a compression technique for autoregressive models that is driven by an imitation learning perspective on knowledge distillation.  ...  Acknowledgments We thank the ASAPP NLP team -especially Yi Yang, Nicholas Matthews, Joshua Shapiro, Hugh Perkins, Amit Ganatra, Lili Yu, Xinyuan Zhang, and Yoav Artzi -as well as the EMNLP reviewers for  ...  Our experiments were conducted using Flambé, a PyTorch-based model training and evaluation library (Wohlwend et al., 2019) .  ... 
doi:10.18653/v1/2020.emnlp-main.494 fatcat:ywgz4k3ewbfinegy3i2l5mrrwe

The Analysis of Open Source Software and Data for Establishment of GIS Services Throughout the Network in a Mapping Organization at National or International Level

Mehrdad Jafari Salim, P. Boccardo
2014
et tw wo or rk k i in n a a m ma ap pp pi in ng g o or rg ga an ni iz za at ti io on n a at t N Na at ti io on na al l o or r I In nt te er rn na at ti io on na al l l le ev ve el l  ...  ou ur rc ce e s so of ft tw wa ar re e a an nd d D Da at ta a f fo or r e es st ta ab bl li is sh hm me en nt t o of f G GI IS S s se er rv vi ic ce es s t th hr ro ou ug gh ho ou ut t t th he e n ne  ...  Mapbender grants access to individuals, groups and manages machine-to-machine access.  ... 
doi:10.6092/polito/porto/2540693 fatcat:eid3tyuhsrattck633ho6vsjwu