找回密码
 立即注册

微信扫一扫,快捷登录!

1

主题

1

帖子

13

积分

Rookie

Rank: 1

积分
13
 楼主| 发表于 2023-5-6 14:54:01 | 显示全部楼层 |阅读模式
澳大利亚南澳大学(University of South Australia: UniSA) 4LLab Data Analytics group 招收全奖博士

1. 招生类型:博士生 (Ph.D.)
2. 招生学校:澳大利亚南澳大学(University of South Australia: UniSA)
3. 研究方向:数据挖掘
4. 入学时间:全年
5. 提供的补助待遇:全奖$32000(含学费保险和生活补助)
6. 招生要求 (拥有以下背景优先考虑):
a. 勤奋、踏实、具有较强烈的学习探索欲望和自我驱动力;
b. 有良好编程背景;
d. 有较为扎实的数学基础;
f. 雅思6.5及以上(小分不低于6分,接受同等PTE成绩)。

请感兴趣的同学把你的简历(包括毕业学校、科研经历,本科以及研究生成绩, 语言成绩等信息)以及微信联系方式发往:ziqi.xu@mymail.unisa.edu.au (发送邮件请在标题注明Applying Ph.D. Position)


Title: Assuring competency of machine learning systems through causal explanation

Abstract: The goal of machine learning (ML) systems is prediction accuracy. ML is not concerned with explanations for outcomes and thus is incapable of articulating its competency. With ambiguous cases and cases where there are conflicting opinions between humans and ML models, it is essential for an ML system to explain not only how reached its decision, but also why the other decision options were not taken. There are methods of explanation that are based on statistical associations, but they may not imply causation. We need to focus on the causal explanation for ML which is just starting to emerge in research. The mainstream methods look at the causal impact of structural components of a model – for example, neurons or a layer structure in a neural network on predictions, which is not the explanation we want, since they explain a model instead of predictions. Our project will develop methods to provide a causal explanation for why a prediction is made for a case. We will also develop methods to provide contrasting explanations as to why one prediction and not another is made on a case.

Financial support: A living allowance scholarship of $32,500 per annum is available to eligible applicants, domestic students or international students.

Details: https://www.unisa.edu.au/researc ... ne-learning-systems



欢迎来到水木紫荆书院!
您需要登录后才可以回帖 登录 | 立即注册

本版积分规则

Archiver|手机版|小黑屋|培君水木书院-源自清华的高端学习平台 ( 闽ICP备13013230号 )

GMT+8, 2024-5-13 16:33 , Processed in 0.126968 second(s), 31 queries .

Powered by Discuz! X3.4

Copyright © 2001-2020, Tencent Cloud.

快速回复 返回顶部 返回列表