Deep reinforcement learning (DRL) has shown incredible performance in learning various tasks to the human level. However, unlike human perception, current DRL models connect the entire low-level sensory input to the state-action values rather than exploiting the relationship between and among entities that constitute the sensory input. Because of this difference, DRL needs vast amount of experi...

Covert shifts of visuospatial attention are traditionally assumed to occur in the absence of oculomotor behavior. In contrast, recent behavioral studies have linked attentional cueing effects to the occurrence of microsaccades, small eye movements executed involuntarily during attempted fixation. Here we used a new type of electrophysiological marker to explore the attention-microsaccade relati...

Hypercolumns in area V1 contain frequencyand orientation-selective simple and complex cells for line (bar) and edge coding, plus end-stopped cells for keypoint (vertex) detection. A single-scale (single-frequency) mathematical model of single and double end-stopped cells on the basis of Gabor filter responses was developed by Heitger et al. (1992 Vision Research 32 963-981). We developed an imp...

Adaptive autonomous agents have to learn about the effects of their actions so as to be able to improve their performance and adapt to long term changes. The problem of correlating actions with changes in sensor data is O(n 2 ) and therefore computationally infeasible for any non-trivial application. We propose to make this problem more manageable by using focus of attention. In particular, we ...

We investigate recognition of spontaneous speech using the focus of visual attention as a secondary cue to speech. In our experiment we collected a corpus of eye and speech data where one participant describes a geographical map to another while having their eye movements tracked. Using this corpus we characterise the coupling between eye movement and speech. Speech recognition results are pres...

A major task of visual attention is to focus processing on regions of interest to enable rapid and robust object search. Instead of integrating generic feature extraction into object specific interpretation we strictly pursue a top-down approach. Early features are tuned to selectively respond to task related visual features, i.e., locally discriminative information that is useful in object rec...

Research has shown that regions with conspicuous colours are very effective in attracting attention, and that regions with different textures also play an important role. We present a biologically plausible model to obtain a saliency map for Focus-of-Attention (FoA), based on colour and texture boundaries. By applying grouping cells which are devoted to low-level geometry, boundary information ...

.......................................................................................................................................... v Index of Figures............................................................................................................................xii Index of Tables ...................................................................................................

IONS FOR REINFORCEMENT LEARNING Abstraction is one of the most common ways of scaling up reinforcement learning, along with function approximation and often overlapping with it. There is a rich and varied literature on the topic, going from state-space abstractions that clump similar states together to hierarchical approaches that define either temporally-extended actions or task subdivisions. ...

This paper presents a model for pedagogical agents to use the learner’s attention to detect motivation factors of the learner in interactive learning environments. This model is based on observations from human tutors coaching students in on-line learning tasks. It takes into account the learner’s focus of attention, current task, and expected time required to perform the task. A Bayesian model...