Towards autonomous bootstrapping for life-long learning categorization tasks

Kirstein, Stephan; Wersing, Heiko; Körner, Edgar

doi:10.1109/ijcnn.2010.5596344

Cited by 7 publications

(6 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

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%

Multimodal space representation driven by self-evaluation of predictability

Lefort

Kopinski

Gepperth

2014

4th International Conference on Development and Learning and on Epigenetic Robotics

View full text Add to dashboard Cite

PROPRE is a generic and modular neural learning paradigm that autonomously extracts meaningful concepts of multimodal data flows driven by predictability across modalities in an unsupervised, incremental and online way. For that purpose, PROPRE consists of the combination of projection and prediction. Firstly, each data flow is topologically projected with a self-organizing map, largely inspired from the Kohonen model. Secondly, each projection is predicted by each other map activities, by mean of linear regressions. The main originality of PROPRE is the use of a simple and generic predictability measure that compares predicted and real activities for each modal stream. This measure drives the corresponding projection learning to favor the mapping of predictable stimuli across modalities at the system level (i.e. that their predictability measure overcomes some threshold). This predictability measure acts as a self-evaluation module that tends to bias the representations extracted by the system so that to improve their correlations across modalities. We already showed that this modulation mechanism is able to bootstrap representation extraction from previously learned representations with artificial multimodal data related to basic robotic behaviors [1] and improves performance of the system for classification of visual data within a supervised learning context [2]. In this article, we improve the self-evaluation module of PROPRE, by introducing a sliding threshold, and apply it to the unsupervised classification of gestures caught from two timeof-flight (ToF) cameras. In this context, we illustrate that the modulation mechanism is still useful although less efficient than purely supervised learning.

show abstract

Section: Introductionsupporting

confidence: 65%

Multimodal space representation driven by self-evaluation of predictability

Lefort

Kopinski

Gepperth

2014

4th International Conference on Development and Learning and on Epigenetic Robotics

View full text Add to dashboard Cite

show abstract

“…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%

PROPRE: PROjection and PREdiction for multimodal correlations learning. An application to pedestrians visual data discrimination

Lefort

Gepperth

2014

2014 International Joint Conference on Neural Networks (IJCNN)

View full text Add to dashboard Cite

PROPRE is a generic and modular unsupervised neural learning paradigm that extracts meaningful concepts of multimodal data flows based on predictability across modalities. It consists on the combination of three modules. First, a topological projection of each data flow on a self-organizing map. Second, a decentralized prediction of each projection activity from each others map activities. Third, a predictability measure that compares predicted and real activities. This measure is used to modulate the projection learning so that to favor the mapping of predictable stimuli across modalities. In this article, we use Kohonen map for the projection module, linear regression for the prediction one and we propose multiple generic predictability measures. We illustrate the properties and performances of PROPRE paradigm on a challenging supervised classification task of visual pedestrian data. The modulation of the projection learning by the predictability measure improves significantly classification performances of the system independently of the measure used. Moreover, PROPRE provides a combination of interesting functional properties, such as a dynamical adaptation to input statistic variations, that is rarely available in other machine learning algorithms.

show abstract

“…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%

Evolving a population code for multimodal concept learning

Lee

Seok

Zhang

2011

2011 IEEE Congress of Evolutionary Computation (CEC)

View full text Add to dashboard Cite

We describe an evolutionary method for learning concepts of objects from multimodal data. The proposed method uses a population code (hypernetwork representation), i.e. a collection of codewords (hyperedges) and associated weights, which is adapted by evolutionary computation based on observations of positive and negative examples. The goal of evolution is to find the best compositions and weights of hyperedges to estimate the underlying distribution of the target concepts. We discuss the relationship of this method with estimation of distribution algorithms (EDAs), classifier systems, and ensemble learning methods. We evaluate the method on a suite of image/text benchmarks. The experimental results demonstrate that the evolutionary process successfully discovers salient codewords representing multi-modal feature combinations for describing and distinguishing different concepts. We also analyze how the complexity of the population code evolves as learning proceeds.

show abstract

Towards autonomous bootstrapping for life-long learning categorization tasks

Cited by 7 publications

References 15 publications

Multimodal space representation driven by self-evaluation of predictability

Multimodal space representation driven by self-evaluation of predictability

PROPRE: PROjection and PREdiction for multimodal correlations learning. An application to pedestrians visual data discrimination

Evolving a population code for multimodal concept learning

Contact Info

Product

Resources

About