The 2010 International Joint Conference on Neural Networks (IJCNN) 2010
DOI: 10.1109/ijcnn.2010.5596344
|View full text |Cite
|
Sign up to set email alerts
|

Towards autonomous bootstrapping for life-long learning categorization tasks

Abstract: Abstract-We present an exemplar-based learning approach for incremental and life-long learning of visual categories. The basic concept of the proposed learning method is to subdivide the learning process into two phases. In the first phase we utilize supervised learning to generate an appropriate category seed, while in the second phase this seed is used to autonomously bootstrap the visual representation. This second learning phase is especially useful for assistive systems like a mobile robot, because the vi… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
4
1

Citation Types

1
5
0

Year Published

2011
2011
2014
2014

Publication Types

Select...
4
1

Relationship

0
5

Authors

Journals

citations
Cited by 7 publications
(6 citation statements)
references
References 15 publications
1
5
0
Order By: Relevance
“…Thus, we define such a processing as multimodal as the data flows may come from different senses, even if in this article we consider multiple data flows coming from the same kind of sensor, as a first study. This work fits in the currently active research on autonomous and progressive construction of sensory-motor representations in the developmental robotics field [3], [4], [5].…”
Section: Introductionsupporting
confidence: 65%
“…Thus, we define such a processing as multimodal as the data flows may come from different senses, even if in this article we consider multiple data flows coming from the same kind of sensor, as a first study. This work fits in the currently active research on autonomous and progressive construction of sensory-motor representations in the developmental robotics field [3], [4], [5].…”
Section: Introductionsupporting
confidence: 65%
“…According to sensory-motor theories, sensory-motor regularities are one key point for structuring the agent's interaction [1]. Hence, autonomous and progressive construction of sensory-motor representations is currently an active research field in developmental robotics [2], [3], [4]. To tackle this complex problem, we propose to take inspiration from biological agents that are already able to interact with their environment in a structured way.…”
Section: Introductionmentioning
confidence: 99%
“…Because our method does not assume prior distributions and does not estimate the parameters of underlying distributions, it has a big potential for dynamic learning. But the proposed method lacks the life-long learning categorization ability [20]. In future works, we will observe the behavior of the proposed method in dynamic learning environment such as video stream learning by enhancing the dynamic learning ability.…”
Section: Discussionmentioning
confidence: 97%