research-article

Deep Active Learning Through Cognitive Information Parcels

Authors:

Zhengming Ding,

Yun FuAuthors Info & Claims

MM '17: Proceedings of the 25th ACM international conference on Multimedia

Pages 952 - 960

https://doi.org/10.1145/3123266.3123337

Published: 19 October 2017 Publication History

Abstract

In deep learning scenarios, a lot of labeled samples are needed to train the models. However, in practical application fields, since the objects to be recognized are complex and non-uniformly distributed, it is difficult to get enough labeled samples at one time. Active learning can actively improve the accuracy with fewer training labels, which is one of the promising solutions to tackle this problem. Inspired by human being's cognition process to acquire additional knowledge gradually, we propose a novel deep active learning method through Cognitive Information Parcels (CIPs) based on the analysis of model's cognitive errors and expert's instruction. The transformation of the cognitive parcels is defined, and the corresponding representation feature of the objects is obtained to identify the model's cognitive error information. Experiments prove that the samples, selected based on the CIPs, can benefit the target recognition and boost the deep model's performance efficiently. The characterization of cognitive knowledge can avoid the other samples' disturbance to the cognitive property of the model effectively. We believe that our work could provide a trial of thought about the cognitive knowledge used in deep learning field.

References

[1]

Asim Bhatti, Kendall H Lee, Hamid Garmestani, and Chee Peng Lim. 2017. Emerging Trends in Neuro Engineering and Neural Computation. Springer.

Digital Library

[2]

Charles Blundell, Julien Cornebise, Koray Kavukcuoglu, and Daan Wierstra. 2015. Weight uncertainty in neural networks.arXiv preprint arXiv:1505.05424(2015).

Digital Library

[3]

Danilo Bzdok and BT Yeo. 2016. The Future of Data Analysis in the Neurosciences. arXiv preprint arXiv:1608.03465 (2016).

[4]

Alfredo Canziani, Adam Paszke, and Eugenio Culurciello. 2016. An Analysis of Deep Neural Network Models for Practical Applications. arXiv preprint arXiv:1605.07678 (2016).

[5]

Patricia S Churchland and Terrence J Sejnowski. 2016. Blending computational and experimental neuroscience. Nature Reviews Neuroscience 17 (2016), 667--668.

[6]

David A Cohn, Zoubin Ghahramani, and Michael I Jordan. 1996. Active learning with statistical models. Journal of artificial intelligence research 4, 1 (1996), 129--145.

Digital Library

[7]

Feras Dayoub, Niko Sünderhauf, and Peter Corke. 2017. Episode-Based Active Learning with Bayesian Neural Networks. arXiv preprint arXiv:1703.07473 (2017).

[8]

Zhengming Ding, Ming Shao, and Yun Fu. 2016. Incomplete Multisource Transfer Learning. IEEE Transactions on Neural Networks and Learning Systems PP, 99 (2016), 1--14.

[9]

Chris Eliasmith, Terrence C Stewart, Xuan Choo, Trevor Bekolay, Travis De-Wolf, Yichuan Tang, and Daniel Rasmussen. 2012. A large-scale model of the functioning brain. science 338, 6111 (2012), 1202--1205.

[10]

Yarin Gal. 2016. Uncertainty in Deep Learning. Ph.D. Dissertation. University of Cambridge.

[11]

Yarin Gal and Zoubin Ghahramani. 2015. Dropout as a Bayesian approximation: Representing model uncertainty in deep learning. arXiv preprint arXiv:1506.021422 (2015).

[12]

Yarin Gal, Riashat Islam, and Zoubin Ghahramani. 2016. Deep Bayesian Active Learning with Image Data. In Bayesian Deep Learning workshop, NIPS, 2016. 1--10.

[13]

Zoubin Ghahramani. 2015. Probabilistic machine learning and artificial intelligence. Nature 521, 7553 (2015), 452--459.

[14]

Peter P Groumpos. 2016. Deep Learning vs. Wise Learning: A Critical and Challenging Overview. IFAC-PapersOnLine 49, 29 (2016), 180--189.

[15]

Carole Hamilton. 2016. Critical Thinking for Better Learning: New Insights from Cognitive Science. Rowman & Littlefield.

[16]

Mahmudul Hasan and Amit K Roy-Chowdhury. 2015. Context aware active learning of activity recognition models. In Proceedings of the IEEE International Conference on Computer Vision. 4543--4551.

Digital Library

[17]

John AC Hattie and Gregory M Donoghue. 2016. Learning strategies: a synthesis and conceptual model. Science of Learning 1 (2016), 16013.

[18]

Andreas Holzinger. 2016. Interactive machine learning for health informatics: when do we need the human-in-the-loop? Brain Informatics 3, 2 (2016), 119--131.

[19]

Neil Houlsby, Ferenc Huszar, Zoubin Ghahramani, and Máté Lengyel. 2011. Bayesian active learning for classification and preference learning. arXiv preprint arXiv:1112.5745(2011).

[20]

Sandra Iglesias, Sara Tomiello, Maya Schneebeli, and Klaas E Stephan. 2016. Models of neuromodulation for computational psychiatry. Wiley Interdisciplinary Reviews: Cognitive Science (2016), 1--22.

[21]

Ajay J Joshi, Fatih Porikli, and Nikolaos Papanikolopoulos. 2009. Multi-class active learning for image classification. In Computer Vision and Pattern Recognition, 2009. CVPR 2009. IEEE Conference on. IEEE, 2372--2379.

[22]

Alex Kendall and Yarin Gal. 2017. What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision? arXiv preprint arXiv:1703.04977 (2017).

[23]

Diederik P Kingma and Max Welling. 2013. Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114 (2013).

[24]

Yu Kong, Ming Shao, Kang Li, and Yun Fu. 2017. Probabilistic Low-Rank Multitask Learning. IEEE Transactions on Neural Networks and Learning Systems PP, 99 (2017), 1--11.

[25]

Yu Kong, Zhiqiang Tao, and Yun Fu. 2017. Deep Sequential Context Networks for Action Prediction. In CVPR 2017.

[26]

Iuliia Kotseruba, Oscar J. Avella Gonzalez, and John K. Tsotsos. 2016. A Review of 40 Years of Cognitive Architecture Research: Focus on Perception, Attention, Learning and Applications. CoRR abs/1610.08602 (2016).

[27]

Iuliia Kotseruba, Oscar J Avella Gonzalez, and John K Tsotsos. 2016. A Review of 40 Years of Cognitive Architecture Research: Focus on Perception, Attention, Learning and Applications. arXiv preprint arXiv:1610.08602 (2016).

[28]

Daniel Kottke, Georg Krempl, and Myra Spiliopoulou. 2015. Probabilistic Active Learning in Datastreams. In International Symposium on Intelligent Data Analysis. Springer, 145--157.

[29]

Georg Krempl, Daniel Kottke, and Vincent Lemaire. 2015. Optimised probabilistic active learning (OPAL). Machine Learning 100, 2--3 (2015), 449--476.

Digital Library

[30]

John P Lalor, Hao Wu, Tsendsuren Munkhdalai, and Hong Yu. 2017. An Analysis of Machine Learning Intelligence. arXiv preprint arXiv:1702.04811 (2017).

[31]

Yann LeCun, Yoshua Bengio, and Geoffrey Hinton. 2015. Deep learning. Nature 521, 7553 (2015), 436--444.

[32]

Lihua Lei and Michael I Jordan. 2016. Less than a Single Pass: Stochastically Controlled Stochastic Gradient Method. arXiv preprint arXiv:1609.03261 (2016).

[33]

Bo-hu Li, Bao-cun Hou, Wen-tao Yu, Xiao-bing Lu, and Chun-wei Yang. 2017. Applications of artificial intelligence in intelligent manufacturing: a review. Frontiers of Information Technology & Electronic Engineering 18, 1 (2017), 86--96.

[34]

Xin Li and Yuhong Guo. 2013. Adaptive active learning for image classification. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 859--866.

Digital Library

[35]

Xin Li, Yuhong Guo, and Dale Schuurmans. 2015. Semi-supervised zero-shot classification with label representation learning. In Proceedings of the IEEE International Conference on Computer Vision. 4211--4219.

Digital Library

[36]

Adam H Marblestone, Greg Wayne, and Konrad P Kording. 2016. Toward an integration of deep learning and neuroscience. Frontiers in Computational Neuroscience 10 (2016), 1--41.

[37]

Allison Master, Andrew N Meltzoff, and Roberto Lent. 2017. Neuroscience, psychology, and society: Translating research to improve learning. Prospects (2017), 1--8.

[38]

Radford M Neal. 2012. Bayesian learning for neural networks. Vol. 118. Springer Science & Business Media.

[39]

Thomas J Palmeri, Bradley C Love, and Brandon M Turner. 2016. Model-based cognitive neuroscience. Journal of Mathematical Psychology 76 (2016), 59--64.

[40]

Soujanya Poria, Erik Cambria, Rajiv Bajpai, and Amir Hussain. 2017. A review of affective computing: From unimodal analysis to multimodal fusion. Information Fusion 37 (2017), 98--125.

Digital Library

[41]

Tim Salimans, Diederik P Kingma, Max Welling, and others. 2015. Markov Chain Monte Carlo and Variational Inference: Bridging the Gap. In ICML, Vol. 37. 1218--1226.

Digital Library

[42]

Tobias Schetter, Christian Decomain, and Stefan Wrobel. 2001. Active hidden markov models for information extraction. In International Symposium on Intelligent Data Analysis. Springer, 309--318.

Digital Library

[43]

Burr Settles and Mark Craven. 2008. An analysis of active learning strategies for sequence labeling tasks. In Proceedings of the conference on empirical methods in natural language processing. Association for Computational Linguistics, 1070--1079.

Digital Library

[44]

Shai Shalev-Shwartz, Ohad Shamir, and Shaked Shammah. 2017. Failures of Deep Learning. arXiv preprint arXiv:1703.07950 (2017).

[45]

Claude Elwood Shannon. 2001. A mathematical theory of communication. ACM SIGMOBILE Mobile Computing and Communications Review 5, 1 (2001), 3--55.

Digital Library

[46]

Olivier Sigaud and Alain Droniou. 2016. Towards deep developmental learning. IEEE Transactions on Cognitive and Developmental Systems 8, 2 (2016), 99--114.

[47]

Nitish Srivastava, Geoffrey E Hinton, Alex Krizhevsky, Ilya Sutskever, and Ruslan Salakhutdinov. 2014. Dropout: a simple way to prevent neural networks from overfitting. Journal of Machine Learning Research 15, 1 (2014), 1929--1958.

Digital Library

[48]

Vivienne Sze, Yu-Hsin Chen, Tien-Ju Yang, and Joel Emer. 2017. Efficient Processing of Deep Neural Networks: A Tutorial and Survey. arXiv preprint arXiv:1703.09039 (2017).

[49]

Brandon M Turner, Birte U Forstmann, Bradley C Love, Thomas J Palmeri, and Leendert Van Maanen. 2017. Approaches to analysis in model-based cognitive neuroscience. Journal of Mathematical Psychology 76 (2017), 65--79.

[50]

Kurt VanLehn, Lishan Zhang, Winslow Burlson, Sylvie Girard, and Yoalli Hidago-Pontet. 2016. Can an non-cognitive learning companion increase the effectiveness of a meta-cognitive learning strategy? IEEE Transactions on Learning Technologies PP, 99 (2016), 1--15.

[51]

Meng Wang and Yi Fang. 2016. Global Consistent Shape Correspondence for Efficient and Effective Active Shape Models. In Proceedings of the 2016 ACM on Multimedia Conference. ACM, 556--560.

Digital Library

[52]

Katsumi Watanabe. 2017. Explicit and implicit aspects of human cognition and behavior. In Knowledge and Smart Technology (KST), 2017 9th International Conference on. IEEE, XVIII--XVIII.

[53]

William Douglas Woody and Wayne Viney. 2017. A history of psychology: The emergence of science and applications. William Douglas Woody and Wayne Viney.

[54]

Zhaohui Wu, Nenggan Zheng, Shaowu Zhang, Xiaoxiang Zheng, Liqiang Gao, and Lijuan Su. 2016. Maze learning by a hybrid brain-computer system. Scientific Reports 6 (2016), 1--12.

[55]

Zizhao Zhang, Fuyong Xing, Xiaoshuang Shi, and Lin Yang. 2016. SemiContour: A Semi-supervised Learning Approach for Contour Detection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 251--259.

[56]

Nan-ning Zheng, Zi-yi Liu, Peng-ju Ren, Yong-qiang Ma, Shi-tao Chen, Si-yu Yu, Jian-ru Xue, Ba-dong Chen, and Fei-yue Wang. 2017. Hybrid-augmented intelligence: collaboration and cognition. Frontiers of Information Technology & Electronic Engineering 18, 2 (2017), 153--179

Cited By

Yang JZhao WLu MHuang J(2023)Deep Active Recognition through Online Cognitive LearningInternational Journal of Pattern Recognition and Artificial Intelligence10.1142/S021800142352013437:09Online publication date: 14-Jul-2023
https://doi.org/10.1142/S0218001423520134
Ren PXiao YChang XHuang PLi ZGupta BChen XWang X(2021)A Survey of Deep Active LearningACM Computing Surveys10.1145/347229154:9(1-40)Online publication date: 8-Oct-2021
https://dl.acm.org/doi/10.1145/3472291
Renuka SAnnadhason A(2019)Mil based lung CT-image classification using CNNHealth and Technology10.1007/s12553-019-00300-zOnline publication date: 7-Feb-2019
https://doi.org/10.1007/s12553-019-00300-z

Index Terms

Deep Active Learning Through Cognitive Information Parcels
1. Computer systems organization
  1. Architectures
    1. Other architectures
      1. Neural networks

Recommendations

Adaptive graph active learning with mutual information via policy learning
Abstract
Graph neural networks entail massive labeled samples for training, and manual labeling generally requires unaffordable costs. Active learning has emerged as a promising approach to selecting a smaller set of informative labeled samples to improve ...
Highlights
- Leverage the mutual information metric to guarantee diversity of the selected nodes.
- Improve the interpretability of active learning.
- Employ an active learning algorithm integrated with reinforcement learning.
Active Learning for kNN Using Instance Impact
AI 2022: Advances in Artificial Intelligence
Abstract
Labelling unlabeled data is a time-consuming and expensive process. Labelling initiatives should select samples that are likely to enhance the classification accuracy of the classifier. Several methods can be employed to accomplish this goal. One ...
iSSL-AL: a deep active learning framework based on self-supervised learning for image classification
Abstract
Deep neural networks have demonstrated exceptional performance across numerous applications. However, DNNs require large amounts of labeled data to avoid overfitting. Unfortunately, the labeled data may not be available; annotating large amounts ...

Comments

Information & Contributors

Information

Published In

cover image ACM Conferences

MM '17: Proceedings of the 25th ACM international conference on Multimedia

October 2017

2028 pages

ISBN:9781450349062

DOI:10.1145/3123266

General Chairs:
Qiong Liu
FXPAL, USA
,
Rainer Lienhart
Universität Augsburg, Germany
,
Haohong Wang
TCL America, USA
,
Program Chairs:
Sheng-Wei "Kuan-Ta" Chen
Academia Sinica, Taiwan
,
Susanne Boll
University of Oldenburg, Germany
,
Phoebe Chen
La Trobe University, Australia
,
Gerald Friedland
Lawrence Livermore National Lab, USA
,
Jia Li
Google, USA
,
Shuicheng Yan
Qihoo 360, China

Copyright © 2017 ACM.

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Sponsors

SIGMM: ACM Special Interest Group on Multimedia

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 19 October 2017

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article

Funding Sources

ONR Young Investigator Award
NSF IIS Award
Chinese State Scholarship Fund
U.S. Army Research Office Young Investigator Award

Conference

MM '17

Sponsor:

SIGMM

MM '17: ACM Multimedia Conference

October 23 - 27, 2017

California, Mountain View, USA

Acceptance Rates

MM '17 Paper Acceptance Rate 189 of 684 submissions, 28%;

Overall Acceptance Rate 2,145 of 8,556 submissions, 25%

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

3
Total Citations
View Citations
227
Total Downloads

Downloads (Last 12 months)7
Downloads (Last 6 weeks)1

Reflects downloads up to 01 Mar 2025

Other Metrics

View Author Metrics

Citations

Cited By

Yang JZhao WLu MHuang J(2023)Deep Active Recognition through Online Cognitive LearningInternational Journal of Pattern Recognition and Artificial Intelligence10.1142/S021800142352013437:09Online publication date: 14-Jul-2023
https://doi.org/10.1142/S0218001423520134
Ren PXiao YChang XHuang PLi ZGupta BChen XWang X(2021)A Survey of Deep Active LearningACM Computing Surveys10.1145/347229154:9(1-40)Online publication date: 8-Oct-2021
https://dl.acm.org/doi/10.1145/3472291
Renuka SAnnadhason A(2019)Mil based lung CT-image classification using CNNHealth and Technology10.1007/s12553-019-00300-zOnline publication date: 7-Feb-2019
https://doi.org/10.1007/s12553-019-00300-z

View Options

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Figures

Tables

Media

View Table of Conten