Deep learning techniques are having an undeniable impact on general pattern recognition issues. In this paper, from a developmental robotics perspective, we scrutinize deep learning techniques under the light of their...
详细信息
Deep learning techniques are having an undeniable impact on general pattern recognition issues. In this paper, from a developmental robotics perspective, we scrutinize deep learning techniques under the light of their capability to construct a hierarchy of meaningful multimodal representations from the raw sensors of robots. These investigations reveal the differences between the methodological constraints of pattern recognition and those of developmental robotics. In particular, we outline the necessity to rely on unsupervised rather than supervised learning methods and we highlight the need for progress towards the implementation of hierarchical predictive processing capabilities. Based on these new tools, we outline the emergence of a new domain that we call deep developmental learning.
There is a large body of work in psychology demonstrating that aesthetic pleasure is a function of the perceiver's cognitive processing dynamics [6]. The current work aims to develop a theoretical account of the p...
详细信息
ISBN:
(纸本)9781450344586
There is a large body of work in psychology demonstrating that aesthetic pleasure is a function of the perceiver's cognitive processing dynamics [6]. The current work aims to develop a theoretical account of the processing dynamics players experience in interacting with computer mediated environments. The present paper integrates the latest theories in Cognitive Science viewing the brain as a Bayesian hierarchicalpredictive machine, and develops insights into the presence illusion experienced in VR and other representational medium. Clark's [3] Bayesian hierarchical predictive processing theory indicates that reuse and redeployment of existing neuronal circuits would both be expected and would be a common and highly effective method to make (re) use of scarce cognitive resources. In the hierarchicalpredictive view of cognition, higher levels of the hierarchy have the goal of reducing prediction error on the generated error signals. We propose that users automatically adapt (typically lower) their expectations at the onset of interactions with virtual environments or other computer mediated environments. In the process of interaction, mismatches between expected and actual signals produce prediction errors and lead to jagged processing fluency. processing fluency is not presence, but presence entails processing fluency.
暂无评论