%0 Generic %1 pansare2018learning %A Pansare, Niketan %A Dusenberry, Michael %A Jindal, Nakul %A Boehm, Matthias %A Reinwald, Berthold %A Sen, Prithviraj %D 2018 %K distributed %T Deep Learning with Apache SystemML %U http://arxiv.org/abs/1802.04647 %X Enterprises operate large data lakes using Hadoop and Spark frameworks that (1) run a plethora of tools to automate powerful data preparation/transformation pipelines, (2) run on shared, large clusters to (3) perform many different analytics tasks ranging from model preparation, building, evaluation, and tuning for both machine learning and deep learning. Developing machine/deep learning models on data in such shared environments is challenging. Apache SystemML provides a unified framework for implementing machine learning and deep learning algorithms in a variety of shared deployment scenarios. SystemML's novel compilation approach automatically generates runtime execution plans for machine/deep learning algorithms that are composed of single-node and distributed runtime operations depending on data and cluster characteristics such as data size, data sparsity, cluster size, and memory configurations, while still exploiting the capabilities of the underlying big data frameworks.

@misc{pansare2018learning, abstract = {Enterprises operate large data lakes using Hadoop and Spark frameworks that (1) run a plethora of tools to automate powerful data preparation/transformation pipelines, (2) run on shared, large clusters to (3) perform many different analytics tasks ranging from model preparation, building, evaluation, and tuning for both machine learning and deep learning. Developing machine/deep learning models on data in such shared environments is challenging. Apache SystemML provides a unified framework for implementing machine learning and deep learning algorithms in a variety of shared deployment scenarios. SystemML's novel compilation approach automatically generates runtime execution plans for machine/deep learning algorithms that are composed of single-node and distributed runtime operations depending on data and cluster characteristics such as data size, data sparsity, cluster size, and memory configurations, while still exploiting the capabilities of the underlying big data frameworks.}, added-at = {2018-02-14T21:21:38.000+0100}, author = {Pansare, Niketan and Dusenberry, Michael and Jindal, Nakul and Boehm, Matthias and Reinwald, Berthold and Sen, Prithviraj}, biburl = {https://www.bibsonomy.org/bibtex/25c83de7de7ea12d3188384dfdeb771bc/jk_itwm}, description = {Deep Learning with Apache SystemML}, interhash = {7d02778ce4a3154ed43d5ede23751d6e}, intrahash = {5c83de7de7ea12d3188384dfdeb771bc}, keywords = {distributed}, note = {cite arxiv:1802.04647Comment: Accepted at SysML 2018}, timestamp = {2018-02-14T21:21:38.000+0100}, title = {Deep Learning with Apache SystemML}, url = {http://arxiv.org/abs/1802.04647}, year = 2018 }