Abstract not found

How can artificial or natural agents autonomously gain understanding of its own internal (sensory) state? This is an important question not just for physically embodied agents but also for software agents in the information technology environment. In this paper, we investigate this issue in the context of a simple biologically motivated sensorimotor agent. We observe and acknowledge, as many other researchers do, that action plays a key role in providing meaning to the sensory state.

What is available to developmental programs in autonomous mental development, and what should be learned at the very early stages of mental development? Our observation is that sensory and motor primitives are the most basic components present at the beginning, and what developmental agents need to learn from these resources is what their internal sensory states stand for. In this paper, we investigate the question in the context of a simple biologically motivated visuomotor agent. We observe and acknowledge, as many other researchers do, that action plays a key role in providing content to the sensory state. We propose a simple, yet powerful learning criterion, that of invariance, where invariance simply means that the internal state does not change over time. We show that after reinforcement learning based on the invariance criterion, the property of action sequence based on an internal sensory state accurately reflects the property of the stimulus that triggered that internal state. That way, the meaning of the internal sensory state can be firmly grounded on the property of that particular action sequence. We expect the framing of the problem and the proposed solution presented in this paper to help shed new light on autonomous understanding in developmental agents such as humanoid robots.

Summary. How can agents, natural or artificial, learn about the external environment based only on its internal state (such as the activation patterns in the brain)? There are two problems involved here: first, forming the internal state based on sensory data to reflect reality, and second, forming thoughts and desires based on these internal states. (Aristotle termed these passive and active intellect, respectively [1].) How are these to be accomplished? Chapters in this book consider mechanisms of the instinct for learning (chapter PERLOVSKY) and reinforcement learning (chapter IFTEKHARUDDIN; chapter WERBOS), which modify the mind’s representation for better fitting sensory data. Our approach (as those in chapters FREEMAN and KOZMA) emphasizes the importance of action in this process. Action plays a key role in recovering sensory stimulus properties that are represented by the internal state. Generating the right kind of action is essential to decoding the internal state. Action that maintains invariance in the internal state are important as it will have the same property as that of the represented sensory stimulus. However, such an approach alone does not address how it can be generalized to learn more complex

EEG containing EMG Objective: To evaluate rapid changes in regional EEG synchronization in normal subjects with spatial and temporal resolution exceeding prior art 10fold. Methods: A curvilinear array of 64 electrodes 3 mm apart extending 18.9 cm across the scalp was used to record EEG at 200/s. Analytic amplitude (AA) and phase (AP) were calculated at each time step for the 64 traces in the analog pass band of 0.5-120 Hz. AP differences approximated the AP derivative (instantaneous frequency). The AP from unfiltered EEG revealed no reproducible patterns. Filtering was necessary in the beta and gamma ranges according to a technique that optimized the correlation of the AP differences with the activity band pass filtered in the alpha range. Results: The sizes of temporal AP differences were usually within ±0.5 radian from the average step corresponding to the center frequency of the pass band. Large AP differences were often synchronized over distances of 6 to 19

integration of natural stimuli

journal homepage: www.elsevier.com/locate/ynimg