開催日時・場所

2019.5.11

国立情報学研究所

プログラム

セッション 1：SysML 参加報告＆紹介

報告者：今井、宮崎

セッション2：Securyt and Privacy

GGREGATHOR: Byzantine Machine Learning via Robust Gradient Aggregation

紹介者：Hiroshi Maruyama

Towards Fedeearning at Scale: System Design

紹介者：今井（代理）

To compress or not to compress: Understanding the Interactions between Adversarial Attacks and Neural Network Compression

紹介者：今井（代理）

セッション3：Hardware & Debugging

Full Deep Neural Network Training on a Pruned Weight Budget

紹介者：今井（代理）

Continuous Integration of Machine Learning Models with ease.ml/ci: Towards a Rigorous Yet Practical Treatment

紹介者：YasuhiroWatanabe

Data Validation for Machine Learning

紹介者：NSK

セッション4：Efficient Training & Interface

Optimizing DNN Computation with Relaxed Graph Substitutions

紹介者：Harumichi Yokoyama

セッション5：Programming Models

TensorFlow Eager: A multi-stage, Python-embedded DSL for machine learning

紹介者：akihiroshinmori

connpass

• : https://mlxse.connpass.com/event/126116/