Template.info

A collection of templates for small and medium-sized enterprises (SME)

Web Development

Media Roundup

By

Preferred Networks Releases Optuna v1.0, Open-source Hyperparameter Optimization Framework for Machine Learning

By

Preferred Networks, Inc. (PFN, Head Office: Tokyo, President & CEO: Toru Nishikawa) has released Optuna (TM) v1.0, the first major version of the open-source hyperparameter optimization framework for machine learning. Projects using the existing beta version can be updated to Optuna v1.0 with minimal changes to the code.

(Logo: https://kyodonewsprwire.jp/prwfile/release/M105870/202001065387/_prw_PI2lg_QDnpjE8Q.jpg)

In machine learning and deep learning, it is critical that complex hyperparameters (*1), which control the behavior of an algorithm during the training process, are optimized to deliver a trained model with better accuracy.

Optuna automates the trial-and-error process of optimizing hyperparameters. It finds hyperparameter values that enable the algorithm to give good performance. Since its beta version release as open-source software (OSS) in December 2018, Optuna has received development support from numerous contributors and added a number of new features based on feedbacks from the OSS community as well as in the company.

Main features of Optuna v1.0 include:

Efficient hyperparameter tuning with state-of-the-art optimization algorithms
Support for various machine learning libraries including PyTorch, TensorFlow, Keras, FastAI, scikit-learn, LightGBM, and XGBoost
Support for parallel execution across multiple computing machines to significantly reduce the optimization time
Search space can be described by Python control statements
Various visualization techniques that allow users to conduct diverse analyses of the optimization results
Official website of Optuna: https://optuna.org/

Optuna has received many contributions from external developers. PFN will continue to quickly incorporate the results of the latest machine learning research into the development of Optuna and work with the OSS community to promote the use of Optuna.

(*1) Hyperparameters include learning rate, batch size, number of training iterations, number of neural network layers, and number of channels.

About the hyperparameter optimization framework for machine learning Optuna (TM)

Optuna was open-sourced by PFN in December 2018 as a hyperparameter optimization framework written in Python. Optuna automates the trial-and-error process of finding hyperparameters that deliver good performance. Optuna is used in many PFN projects and was an important factor in PFDet team’s award-winning performances in the first Kaggle Open Images object detection competition.

About Preferred Networks (PFN)

PFN was founded in March 2014 with the aim of promoting business utilization of deep learning and robotics technologies. PFN aims to drive innovations mainly in the three priority business areas of transportation systems, manufacturing, and bio/healthcare in collaboration with leading companies and organizations.

PFN developed the open-source deep learning framework Chainer (TM) in 2015 and demonstrated a fully autonomous tidying-up robot system at CEATEC 2018. In 2020, PFN plans to operate a supercomputer equipped with MN-Cor (TM), a deep learning processor developed by PFN. The range of its deep learning applications has been expanded to include areas such as personal robots, plant optimization, material search, sports analysis, and entertainment.

https://www.preferred.jp/en/

*Optuna (TM), Chainer (TM), and MN-Core (TM) are the trademarks or the registered trademarks of Preferred Networks, Inc. in Japan and elsewhere.

SOURCE Preferred Networks, Inc.

トップページ（日本語版）

GraphDB 9.1 – the Database to Support High-quality Knowledge Graphs

By

Deliver faster, cheaper and higher-quality knowledge graph with RDF validation and versioning

Ontotext is happy to announce the 9.1 release of GraphDB – the most powerful database optimized for the development and maintenance of knowledge graphs.

Knowledge graphs are the next generation tool for taking important business decisions based on harmonized knowledge models derived from siloed source systems. A key challenge is to maintain the graph up to date with the upstream systems. GraphDB already supports a highly efficient mechanism for to replace sub-graphs (named graphs), which eliminates the need for developing incremental updates.

In 9.1, the database now offers multiple important features to improve the knowledge graph delivery process further:

Validation of all newly inserted RDF with SHACL validation schema to guarantee that the knowledge graph will automatically preserve its high quality after each update.
Tracking of all changes in the current active or past committed transactions. GraphDB will maintain a configurable provenance of all knowledge graph updates.
Kerberos support to improve security in large enterprise networks.
Ontotext’s product team is eager to continue improving the core features of GraphDB 9 as well as to develop exciting new features so that users can easily and efficiently create their enterprise knowledge graph solutions.

About Ontotext

For over two decades Ontotext has brought together knowledge, data and analytics transforming how organizations identify meaning across diverse databases and massive amounts of unstructured data through knowledge graphs.

Ontotext makes tailor-made solutions across multiple sectors: media and publishing, healthcare and life sciences, government and cultural heritage, financial services and more. Their client list includes news and media agencies like the BBC and Financial Times, top Academic publishers like Elsevier, Springer Nature and Wiley, leading pharmacological companies such as AstraZeneca, public institutions including the UK Parliament, Kadastr.NL and US Department of Defense, and cultural institutions like the British Museum, The National Gallery of USA and Getty Trust.

SOURCE Ontotext

New templates:
newsletter.knowledgeengineering.com
b2b.jvq.net
survey.zgm.org
briefing.msl.net