MALMIR, SIKKA, FORSTER, MOVELLAN, COTTRELL: ACTIVE RECOGNITION OF GERMS1 Deep Q-learning for Active Recognition of GERMS: Baseline performance on a standardized dataset for active learning

نویسندگان

  • Mohsen Malmir
  • Karan Sikka
  • Deborah Forster
  • Javier Movellan
  • Garrison W. Cottrell
چکیده

In this paper, we introduce GERMS, a dataset designed to accelerate progress on active object recognition in the context of human robot interaction. GERMS consists of a collection of videos taken from the point of view of a humanoid robot that receives objects from humans and actively examines them. GERMS provides methods to simulate, evaluate, and compare active object recognition approaches that close the loop between perception and action without the need to operate physical robots. We present a benchmark system for active object recognition based on deep Q-learning (DQL). The system learns to actively examine objects by minimizing overall classification error using standard back-propagation and Q-learning. DQL learns an efficient policy that achieves high levels of accuracy with short observation periods.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Deep Q-learning for Active Recognition of GERMS: Baseline performance on a standardized dataset for active learning

Mohsen Malmir1 http://mplab.ucsd.edu/~mmalmir/ Karan Sikka1 http://mplab.ucsd.edu/~ksikka/ Deborah Forster1 [email protected] Javier Movellan2 http://www.emotient.com/ Garrison W. Cottrell3 http://cseweb.ucsd.edu/~gary/ 1 Machine Perception Lab. University of California San Diego, San Diego, CA, USA 2 Emotient, Inc. 4435 Eastgate Mall, Suite 320, San Diego, CA, USA 3 Computer Science and Engine...

متن کامل

Deep active object recognition by joint label and action prediction

An active object recognition system has the advantage of acting in the environment to capture images that are more suited for training and lead to better performance at test time. In this paper, we utilize deep convolutional neural networks for active object recognition by simultaneously predicting the object label and the next action to be performed on the object with the aim of improving reco...

متن کامل

CRFA-CRBM: a hybrid technique for anomaly recognition in regional geochemical exploration; case study: Dehsalm area, east of Iran

Identification of geochemical anomalies is a significant step during regional geochemical exploration. In this matter, new techniques have been developed based on deep learning networks. These simple-structure-networks act like our brains on processing the data by simulating deep layers of thinking. In this paper, a hybrid compositional-deep learning technique was applied to identify the anomal...

متن کامل

Active Learning: An Approach for Reducing Theory-Practice Gap in Clinical Education

Introduction: The gap between theory and practice in clinical fields, including nursing, is one of the main problems that many solutions have been suggested to eliminate it. In this article, we have tried to investigate its solution through active learning. Methods: In this review article, searching articles published during 2000-2012 was done through library references, scientific databases. ...

متن کامل

Named Entity Recognition in Persian Text using Deep Learning

Named entities recognition is a fundamental task in the field of natural language processing. It is also known as a subset of information extraction. The process of recognizing named entities aims at finding proper nouns in the text and classifying them into predetermined classes such as names of people, organizations, and places. In this paper, we propose a named entity recognizer which benefi...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2015