Emergence of verb and object concepts through learning affordances

Download
2010
Dağ, Nilgün
Researchers are still far from thoroughly understanding and building accurate computational models of the mechanisms in human mind that give rise to cognitive processes such as emergence of concepts and language acquisition. As a new attempt to give an insight into this issue, in this thesis, we are concerned about developing a computational model that leads to the emergence of concepts. Speci cally, we investigate how a robot can acquire verb and object concepts through learning affordances, a notion first proposed by J. J. Gibson in 1986. Using the affordance formalization framework of Şahin et al. in 2007, a humanoid robot acquires concepts through interactions in an embodied environment. For the acquisition of verb concepts, we take an alternative approach to the literature, which generally links verbs to specific behaviors of the robot, by linking them to specific effects that different behaviors may generate. We show how our robot can learn effect prototypes, represented in terms of feature changes in the perception vector of the robot, through demonstrations made by a human supervisor. As for the object concepts, we use the affordance relations of objects to create object concepts based on their functional relevance. Additionally, we show that the extracted e ect prototypes corresponding to verb concepts can also be utilized to discover stable and variable properties of objects which can be associated to stable and variable affordances. Moreover, we show that the acquired concepts provide a suitable basis for communication with humans or other agents, for example to understand and imitate others' behaviors or for goal speci cation tasks. These capabilities are demonstrated in simple interaction games on the iCub humanoid robot platform.

Suggestions

Learning to Navigate Endoscopic Capsule Robots
Turan, Mehmet; Almalioglu, Yasin; Gilbert, Hunter B.; Mahmood, Faisal; Durr, Nicholas J.; Araujo, Helder; Sari, Alp Eren; Ajay, Anurag; Sitti, Metin (Institute of Electrical and Electronics Engineers (IEEE), 2019-07-01)
Deep reinforcement learning (DRL) techniques have been successful in several domains, such as physical simulations, computer games, and simulated robotic tasks, yet the transfer of these successful learning concepts from simulations into the real world scenarios remains still a challenge. In this letter, a DRL approach is proposed to learn the continuous control of a magnetically actuated soft capsule endoscope (MASCE). Proposed controller approach can alleviate the need for tedious modeling of complex and ...
A temporal neural network model for constructing connectionist expert system knowledge bases
Alpaslan, Ferda Nur (Elsevier BV, 1996-04-01)
This paper introduces a temporal feedforward neural network model that can be applied to a number of neural network application areas, including connectionist expert systems. The neural network model has a multi-layer structure, i.e. the number of layers is not limited. Also, the model has the flexibility of defining output nodes in any layer. This is especially important for connectionist expert system applications.
Interaction of Spatial Configurations and Language: An Experimental Inquiry
Yılmaz, Naz Buse; Çakır, Murat Perit; Acartürk, Cengiz; Department of Cognitive Sciences (2022-8-31)
The perception and description of space are one of the most fundamental phenomena in human cognition and evolution. Knowing where we are and telling allies about it is vital information from an evolutionary perspective. There is more than one way to define spatial scenes, and we choose one of these ways without even realizing it. Literature examines the spatial linguistic systems to find out what drives and provoke these differences. Linguistic elements that define space generally examined as topological de...
A mathematical contribution of statistical learning and continuous optimization using infinite and semi-infinite programming to computational statistics
Özöğür-Akyüz, Süreyya; Weber, Gerhard Wilhelm; Department of Scientific Computing (2009)
A subfield of artificial intelligence, machine learning (ML), is concerned with the development of algorithms that allow computers to “learn”. ML is the process of training a system with large number of examples, extracting rules and finding patterns in order to make predictions on new data points (examples). The most common machine learning schemes are supervised, semi-supervised, unsupervised and reinforcement learning. These schemes apply to natural language processing, search engines, medical diagnosis,...
Prototype Hardware Design for Brain Computer Interface Applications
Erdogan, Balkar; Akinci, Berna; Acar, Erman; Usakli, Ali Buelent; Gençer, Nevzat Güneri (2009-01-01)
Brain Computer Interface (BCI) is an alternative communication pathway between the human brain and outside world in which only the brain activity is interpreted in a special way. These systems are based on the electrical activity of the brain that can be measured via Electroencephalography (EEG) devices. BCI enables people with severe motor disorders (like ALS) to communicate with their environment or control a wheelchair for their movement by using the EEG signals. In this study, a prototype data acquisito...
Citation Formats
N. Dağ, “Emergence of verb and object concepts through learning affordances,” M.S. - Master of Science, Middle East Technical University, 2010.