Mental development and representation building through motivated learning
The 2010 International Joint Conference on Neural Networks (IJCNN), 2010
ABSTRACT Motivated learning is a new machine learning approach that extends reinforcement learnin... more ABSTRACT Motivated learning is a new machine learning approach that extends reinforcement learning idea to dynamically changing, and highly structured environments. In this approach a machine is capable of defining its own objectives and learns to satisfy them though an internal reward system. The machine is forced to explore the environment in response to externally applied negative (pain) signals that it must minimize. In doing so, it discovers relationships between objects observed through its sensory inputs and actions it performs on the observed objects. Observed concepts are not predefined but are emerging as a result of successful operations. For the optimum development of concepts and related skills, the machine operates in the protective environment that gradually increases its complexity. Simulation illustrates the advantage of this gradual increase in environment complexity for machine development. Comparison to reinforcement learning indicates weakness of the later method in learning proper behavior, even in such protective environments with gradually increasing complexity. The method shows how mental development stimulates learning of new concepts and at the same time benefits from this learning. Thus the method addresses a well know problem of merging connectionist (bottom-up) and symbolic (top down) approaches for intelligent autonomous machine operation in developmental robotics.
The 2011 International Joint Conference on Neural Networks, 2011
Motivated learning (ML) is a new biologically inspired machine learning method. It is the combina... more Motivated learning (ML) is a new biologically inspired machine learning method. It is the combination of a reinforcement learning (RL) algorithm and a system that creates hierarchy of goals. The goal creation system is concerned with creating new internal goals, building a hierarchy of them, and controlling the agent's behavior according to this constituted hierarchy of goals. As in case of reinforcement learning method, a motivated learning agent is learning through interaction with the environment. The comparisons of both methods in special type test environment show that the motivated learning method is more efficient in learning complex relations between available resources (concepts). ML has better performance than RL, especially in dynamically changing environments. In the presented experiments we have shown that ML based agent, which has the ability to set its internal goals autonomously, is able to fulfill the designer's goals more effectively than RL based agent. In addition, because the observed concepts are not predefined but emerge during the learning process, this method also addresses problem of merging connectionist and symbolic approaches for intelligent autonomous systems.
2013 IEEE Symposium on Computational Intelligence in Healthcare and e-health (CICARE), 2013
ABSTRACT The paper describes a test-bench model for braincomputer interface research based on EEG... more ABSTRACT The paper describes a test-bench model for braincomputer interface research based on EEG signals. The test-bench is going to be used for students training and education. The goal is to prepare modern Brain-Computer Interface development environment in order to create interest about this topic among the students.
Abstract The rapid growth in availability of new biomedical systems and devices capable of acquir... more Abstract The rapid growth in availability of new biomedical systems and devices capable of acquiring biosignals for disease diagnosis and health monitoring require rigorous processing. Biomedical research by nature depends on integrated problem solving software environment and often involves people located at different geographical positions. The reusability of different personalized tools are limited due to the complex architectural constrains and restricted interoperability among different devices mostly requiring ...
A new machine learning approach known as motivated learning (ML) is presented in this work. Motiv... more A new machine learning approach known as motivated learning (ML) is presented in this work. Motivated learning drives a machine to develop abstract motivations and choose its own goals. ML also provides a self-organizing system that controls a machine's behavior based on competition between dynamically-changing pain signals. This provides an interplay of externally driven and internally generated control signals. It is demonstrated that ML not only yields a more sophisticated learning mechanism and system of values than reinforcement learning (RL), but is also more efficient in learning complex relations and delivers better performance than RL in dynamically changing environments. In addition, this paper shows the basic neural network structures used to create abstract motivations, higher level goals, and subgoals. Finally, simulation results show comparisons between ML and RL in environments of gradually increasing sophistication and levels of difficulty.
Cognitive agent and its implementation in the blender game engine environment
ABSTRACT The paper presents a structural model of a cognitive agent and its Blender implementatio... more ABSTRACT The paper presents a structural model of a cognitive agent and its Blender implementation. Built in a virtual world, the agent is able to act autonomously, observe its environment and learn from its actions using principles of motivated learning. We discuss both its organizational structure and tools we used to develop virtual implementation of the agent. In this paper, we explain why it is important to consider cognitive agent's model together with restrictions imposed by its sensory and motor functions and the properties of objects the agent interacts with in the virtual world.
2013 IEEE Symposium on Computational Intelligence in Healthcare and e-health (CICARE), 2013
ABSTRACT This work presents an application of Wireless Sensor Network (WSN) of random access with... more ABSTRACT This work presents an application of Wireless Sensor Network (WSN) of random access with one-way transmission to the monitoring of hospital patients. In the paper, we consider WSN single-hop network using one single radio frequency, such that all nodes are divided into several groups depending on the average time between the transmission due to the different state of health of patients. We apply the Poisson Arrivals See Time Averages (PASTA) to modeling of WSN. We present formula for the probability of collisions which has been verified by simulation studies of network.
Uploads
Papers by Pawel Raif