SEARCH SESSIONS

Search All
 
Refine Results:
 
Year(s)

SOCIAL MEDIA

EMAIL SUBSCRIPTION

 
 

GTC On-Demand

Presentation
Media
Abstract:
We'll introduce a method for constructing an accurate prediction model from limited data in machine learning, one of the most important tasks in machine learning. We'll discuss unsupervised domain adaptation for open set data and a visual question-generation method to acquire knowledge of unknown object categories.
We'll introduce a method for constructing an accurate prediction model from limited data in machine learning, one of the most important tasks in machine learning. We'll discuss unsupervised domain adaptation for open set data and a visual question-generation method to acquire knowledge of unknown object categories.  Back
 
Topics:
AI and DL Research
Type:
Talk
Event:
GTC Silicon Valley
Year:
2019
Session ID:
S9598
Streaming:
Download:
Share:
 
Abstract:
Constructing an accurate prediction model from limited data is one of the important tasks in machine learning. We'll introduce unsupervised domain adaptation and a learning method using interclass patterns as a method to construct accurate prediction models from limited data. Regarding unsupervised domain adaptation, we use three networks asymmetrically. Two networks are used to label unlabeled target patterns, and one network is trained by the pseudo-labeled patterns to obtain target-discriminative representations. About the learning method using interclass patterns, we generate interclass patterns by mixing two patterns belonging to different classes with a random ratio and train the model to output the mixing ratio form the mixed patterns. Although the algorithm is very simple, the proposed method significantly improves classification performance on sound recognition and image recognition. In addition, we'll briefly introduce various topics, including WebDNN, which our team is working on.
Constructing an accurate prediction model from limited data is one of the important tasks in machine learning. We'll introduce unsupervised domain adaptation and a learning method using interclass patterns as a method to construct accurate prediction models from limited data. Regarding unsupervised domain adaptation, we use three networks asymmetrically. Two networks are used to label unlabeled target patterns, and one network is trained by the pseudo-labeled patterns to obtain target-discriminative representations. About the learning method using interclass patterns, we generate interclass patterns by mixing two patterns belonging to different classes with a random ratio and train the model to output the mixing ratio form the mixed patterns. Although the algorithm is very simple, the proposed method significantly improves classification performance on sound recognition and image recognition. In addition, we'll briefly introduce various topics, including WebDNN, which our team is working on.  Back
 
Topics:
AI and DL Research
Type:
Talk
Event:
GTC Silicon Valley
Year:
2018
Session ID:
S8786
Streaming:
Download:
Share: