東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

Learning to Build Probabilistic Mode...

Snell, Jake C.

FindBook

Google Book

Amazon

博客來

Learning to Build Probabilistic Models with Limited Data.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Learning to Build Probabilistic Models with Limited Data./
作者:	Snell, Jake C.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2021,
面頁冊數:	116 p.
附註:	Source: Dissertations Abstracts International, Volume: 83-01, Section: B.
Contained By:	Dissertations Abstracts International83-01B.
標題:	Computer science. -
電子資源:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28318197
ISBN:	9798522943332

Learning to Build Probabilistic Models with Limited Data.
Snell, Jake C.

Learning to Build Probabilistic Models with Limited Data. - Ann Arbor : ProQuest Dissertations & Theses, 2021 - 116 p.

Source: Dissertations Abstracts International, Volume: 83-01, Section: B.

Thesis (Ph.D.)--University of Toronto (Canada), 2021.

This item must not be sold to any third party vendors.

Deep learning has successfully transformed a wide range of machine learning applications in recent years. One of its keys to success is the ability to learn relevant features from scratch on large amounts of data. Yet there are many real-world scenarios in which a new model must be built quickly with only a small amount of data. This naturally raises the question: How can we use deep learning to efficiently build task-specific models given limited data? In this thesis, we introduce a framework for understanding relationships among these sorts of problems and propose several novel algorithms for tackling challenging tasks in this regime including few-shot learning, zero-shot learning, and structured prediction.In the first part of this thesis, we propose a deep metric learning approach to few-shot and zero-shot classification that generalizes from just a few examples. It does so by exploiting a simple inductive bias, namely that there exists an embedding space in which examples from the same class are clustered around a single prototype representation. We demonstrate the strong accuracy of our approach on standard few-shot and zero-shot benchmarks.We then consider image segmentation, an task in which is important for a machine learning system to capture multiple plausible outputs due to ambiguity. We introduce a tree-structured graphical model for representing such distributions and propose an algorithm that optimizes the model structure for each image. When evaluated on a challenging image segmentation datasets, our algorithm is successfully able to generate multiple diverse segmentations much in the way that humans do.Finally, we develop a Bayesian approach to few-shot classification based on Gaussian processes. Our method learns a deep kernel to compute the similarities among input images and uses a Polya-Gamma augmentation scheme to achieve tractable inference. We show strong predictive accuracy on several challenging few-shot learning datasets and improved uncertainty quantification over baseline methods.

ISBN: 9798522943332Subjects--Topical Terms:

523869
Computer science.
Subjects--Index Terms:

Deep Learning

Learning to Build Probabilistic Models with Limited Data.
LDR:03148nmm a2200361 4500 001 2283282
005 20211029084537.5
008 220723s2021 ||||||||||||||||| ||eng d
020 $a 9798522943332
035 $a (MiAaPQ)AAI28318197
035 $a AAI28318197
040 $a MiAaPQ $c MiAaPQ
100 1 $a Snell, Jake C. $3 3562222
245 1 0 $a Learning to Build Probabilistic Models with Limited Data.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2021
300 $a 116 p.
500 $a Source: Dissertations Abstracts International, Volume: 83-01, Section: B.
500 $a Advisor: Zemel, Rich.
502 $a Thesis (Ph.D.)--University of Toronto (Canada), 2021.
506 $a This item must not be sold to any third party vendors.
520 $a Deep learning has successfully transformed a wide range of machine learning applications in recent years. One of its keys to success is the ability to learn relevant features from scratch on large amounts of data. Yet there are many real-world scenarios in which a new model must be built quickly with only a small amount of data. This naturally raises the question: How can we use deep learning to efficiently build task-specific models given limited data? In this thesis, we introduce a framework for understanding relationships among these sorts of problems and propose several novel algorithms for tackling challenging tasks in this regime including few-shot learning, zero-shot learning, and structured prediction.In the first part of this thesis, we propose a deep metric learning approach to few-shot and zero-shot classification that generalizes from just a few examples. It does so by exploiting a simple inductive bias, namely that there exists an embedding space in which examples from the same class are clustered around a single prototype representation. We demonstrate the strong accuracy of our approach on standard few-shot and zero-shot benchmarks.We then consider image segmentation, an task in which is important for a machine learning system to capture multiple plausible outputs due to ambiguity. We introduce a tree-structured graphical model for representing such distributions and propose an algorithm that optimizes the model structure for each image. When evaluated on a challenging image segmentation datasets, our algorithm is successfully able to generate multiple diverse segmentations much in the way that humans do.Finally, we develop a Bayesian approach to few-shot classification based on Gaussian processes. Our method learns a deep kernel to compute the similarities among input images and uses a Polya-Gamma augmentation scheme to achieve tractable inference. We show strong predictive accuracy on several challenging few-shot learning datasets and improved uncertainty quantification over baseline methods.
590 $a School code: 0779.
650 4 $a Computer science. $3 523869
650 4 $a Artificial intelligence. $3 516317
650 4 $a Statistical physics. $3 536281
650 4 $a Information science. $3 554358
650 4 $a Standard deviation. $3 3560390
650 4 $a Accuracy. $3 3559958
650 4 $a Datasets. $3 3541416
650 4 $a Random variables. $3 646291
650 4 $a Experiments. $3 525909
650 4 $a Corruption. $3 615175
650 4 $a Classification. $3 595585
650 4 $a Noise. $3 598816
650 4 $a Confidence intervals. $3 566017
650 4 $a Parameter estimation. $3 567557
653 $a Deep Learning
653 $a Machine Learning
653 $a Probabilistic model
690 $a 0984
690 $a 0800
690 $a 0723
690 $a 0217
710 2 $a University of Toronto (Canada). $b Computer Science. $3 2096342
773 0 $t Dissertations Abstracts International $g 83-01B.
790 $a 0779
791 $a Ph.D.
792 $a 2021
793 $a English
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28318197