Active Machine Learning: From Theory to Practice Robert Nowak 19 March 2018

Duration: 1 hour 4 mins

Share this media item:

Embed this media item:

<iframe width="_width_" height="_height_" src="https://sms.cam.ac.uk/media/2945746/embed" frameborder="0" scrolling="no" allowfullscreen></iframe>

Choose size:

About this item

Available Formats

About this item

Description:	This talk focuses on active ML that close the loop on machine learning, sensing and data collection, and human labeling. Standard (passive) machine learning involves designing a classification rule based on a randomly selected training dataset. Active machine learning algorithms automatically and adaptively select the most informative data for labeling so that human time is not wasted labeling irrelevant or trivial examples. The aim is to make ML as efficient and robust as possible, with a minimal amount of human supervision and assistance. This talk describes ongoing theoretical and experimental work in several areas of active learning

Description:

This talk focuses on active ML that close the loop on machine learning, sensing and data collection, and human labeling. Standard (passive) machine learning involves designing a classification rule based on a randomly selected training dataset. Active machine learning algorithms automatically and adaptively select the most informative data for labeling so that human time is not wasted labeling irrelevant or trivial examples. The aim is to make ML as efficient and robust as possible, with a minimal amount of human supervision and assistance. This talk describes ongoing theoretical and experimental work in several areas of active learning


Created:	2019-03-25 09:55
Collection:	Information Engineering Distinguished Lecture Series
Publisher:	University of Cambridge
Copyright:	Robert Nowack
Language:	eng (English)


Abstract:	The field of ML has advanced considerably in recent years, but mostly in well-defined domains using huge amounts of human-labeled training data. Machines can recognize objects in images and translate text, but they must be trained with more images and text than a person can see in nearly a lifetime. Humans, on the other hand, can learn from far fewer examples, generalize well across tasks and modalities, and perform better than machines at most tasks, especially in complex and unpredictable situations. To address this gap, this talk focuses on active ML that close the loop on machine learning, sensing and data collection, and human labeling. Standard (passive) machine learning involves designing a classification rule based on a randomly selected training dataset. Active machine learning algorithms automatically and adaptively select the most informative data for labeling so that human time is not wasted labeling irrelevant or trivial examples. The aim is to make ML as efficient and robust as possible, with a minimal amount of human supervision and assistance. This talk describes ongoing theoretical and experimental work in several areas of active learning Short biography: Rob is the McFarland-Bascom Professor in Engineering at the University of Wisconsin-Madison, where his research focuses on signal processing, machine learning, optimization, and statistics.

Abstract:

The field of ML has advanced considerably in recent years, but mostly in well-defined domains using huge amounts of human-labeled training data. Machines can recognize objects in images and translate text, but they must be trained with more images and text than a person can see in nearly a lifetime. Humans, on the other hand, can learn from far fewer examples, generalize well across tasks and modalities, and perform better than machines at most tasks, especially in complex and unpredictable situations. To address this gap, this talk focuses on active ML that close the loop on machine learning, sensing and data collection, and human labeling. Standard (passive) machine learning involves designing a classification rule based on a randomly selected training dataset. Active machine learning algorithms automatically and adaptively select the most informative data for labeling so that human time is not wasted labeling irrelevant or trivial examples. The aim is to make ML as efficient and robust as possible, with a minimal amount of human supervision and assistance. This talk describes ongoing theoretical and experimental work in several areas of active learning

Short biography: Rob is the McFarland-Bascom Professor in Engineering at the University of Wisconsin-Madison, where his research focuses on signal processing, machine learning, optimization, and statistics.

Available Formats

Format	Quality	Bitrate	Size
MPEG-4 Video	1280x720	3.01 Mbits/sec	1.41 GB	View	Download
MPEG-4 Video	640x360	1.95 Mbits/sec	939.53 MB	View	Download
WebM	640x360	330.42 kbits/sec	154.89 MB	View	Download
iPod Video	480x270	525.17 kbits/sec	246.17 MB	View	Download
MP3	44100 Hz	252.29 kbits/sec	118.26 MB	Listen	Download
Auto *	(Allows browser to choose a format it supports)