O'Reilly、Cloudera 主办
Make Data Work
2017年7月12-13日:培训
2017年7月13-15日:会议
北京,中国

现实世界里的主动学习 (Active learning in the real world)

This will be presented in English.

Lukas Biewald (Weights & Biases)
11:15–11:55 Saturday, 2017-07-15
英文讲话 (Presented in English)
地点: 报告厅(Auditorium) 观众水平 (Level): Intermediate
平均得分:: ***..
(3.00, 2 次得分)

训练数据的收集策略通常是部署现实世界机器学习算法中最重要却经常被忽视的部分。主动学习是收集训练数据的最佳方法,也是真正能够影响到底是失败的研究项目还是成功上线的算法的重要研究课题之一。这个讲座将涵盖从搜索相关性到自主驾驶汽车的各个领域的主动学习的策略。 它还将涵盖在有限的训练数据的情况下,如何通过细微调整深度学习和其他技术来让它们变的有用的内容。


Training data collection strategies are often the most important and overlooked part of deploying real-world machine learning algorithms. Lukas Biewald explains why active learning is the best way to collect training data and can make the difference between a failed research project and a deployed production algorithm. Lukas shares active learning strategies across domains from search relevance to self-driving cars and explains how fine-tuning deep learning and other techniques are useful in a world of limited training data.

Photo of Lukas Biewald

Lukas Biewald

Weights & Biases

Lukas Biewald is the founder and chief data scientist of Weights & Biases, a data enrichment platform that taps into an on-demand workforce to help companies collect training data and do human-in-the-loop machine learning. Previously, he led the Search Relevance team for Yahoo Japan and worked as a senior data scientist at Powerset. Lukas was recognized by Inc. magazine as a 30 under 30. Lukas holds a BS in mathematics and an MS in computer science from Stanford University. He is also an expert Go player.

联系OReillyData

关注OReillyData微信号获取最新会议信息并浏览前沿数据文章。

WeChat QRcode

 

Stay Connected Image 1
Stay Connected Image 3
Stay Connected Image 2

阅读关于大数据的最新理念。

ORB Data Site