| LDR | | 01996nmm uu200397 4500 |
| 001 | | 000000332735 |
| 005 | | 20240805171504 |
| 008 | | 181129s2018 |||||||||||||||||c||eng d |
| 020 | |
▼a 9780438149977 |
| 035 | |
▼a (MiAaPQ)AAI10811307 |
| 035 | |
▼a (MiAaPQ)bu:13863 |
| 040 | |
▼a MiAaPQ
▼c MiAaPQ
▼d 248032 |
| 082 | 0 |
▼a 621.3 |
| 100 | 1 |
▼a Bolukbasi, Tolga. |
| 245 | 10 |
▼a Machine Learning in the Real World with Multiple Objectives. |
| 260 | |
▼a [S.l.] :
▼b Boston University.,
▼c 2018 |
| 260 | 1 |
▼a Ann Arbor :
▼b ProQuest Dissertations & Theses,
▼c 2018 |
| 300 | |
▼a 169 p. |
| 500 | |
▼a Source: Dissertation Abstracts International, Volume: 79-12(E), Section: B. |
| 500 | |
▼a Adviser: Venkatesh Saligrama. |
| 502 | 1 |
▼a Thesis (Ph.D.)--Boston University, 2018. |
| 520 | |
▼a Machine learning (ML) is ubiquitous in many real-world applications. Existing ML systems are based on optimizing a single quality metric such as prediction accuracy. These metrics typically do not fully align with real-world design constraints s |
| 520 | |
▼a First, we focus on decreasing the test-time computational costs of prediction systems. Budget constraints arise in many machine learning problems. Computational costs limit the usage of many models on small devices such as IoT or mobile phones a |
| 520 | |
▼a In the context of fairness, we first demonstrate that a naive application of ML methods runs the risk of amplifying social biases present in data. This danger is particularly acute for methods based on word embeddings, which are increasingly gai |
| 590 | |
▼a School code: 0017. |
| 650 | 4 |
▼a Electrical engineering. |
| 690 | |
▼a 0544 |
| 710 | 20 |
▼a Boston University.
▼b Electrical & Computer Engineering ENG. |
| 773 | 0 |
▼t Dissertation Abstracts International
▼g 79-12B(E). |
| 773 | |
▼t Dissertation Abstract International |
| 790 | |
▼a 0017 |
| 791 | |
▼a Ph.D. |
| 792 | |
▼a 2018 |
| 793 | |
▼a English |
| 856 | 40 |
▼u http://www.riss.kr/pdu/ddodLink.do?id=T14997970
▼n KERIS |
| 980 | |
▼a 201812
▼f 2019 |
| 990 | |
▼a 관리자 |