Abstract—Vision is basically a sensory modality, so it is no surprise that the investigation into the brain’s visual functions has been focused on its sensory aspect. Thus, questions like (1) how can external geometric properties represented in internal states of the visual system be grounded, (2) how do the visual cortical receptive fields (RFs) form, and (3) how can visual shapes be recognized have all been addressed within the framework of sensory information processing. However, this view is being challenged on multiple fronts, with an increasing emphasis on the motor aspect of visual function. In this paper, we will review works that implicate the important role of motor function in vision, and discuss our latest results touching upon the issues of grounding, RF development, and shape recognition. Our main findings are that (1) motor primitives play a fundamental role in grounding, (2) RF learning can be biased and enhanced by the motor system, and (3) shape recognition is easier with motorbased representations than with sensor-based representations. The insights we gained here will help us better understand visual cortical function. Also, we expect the motor-oriented view of visual cortical function to be generalizable to other sensory cortices such as somatosensory and auditory cortices. I.

• Present: reactive behavior

Simulation in virtual environments has become an integral part in highly technical training programs such as flight simulators for pilot training. Although very complex, these simulators are based on a set of well-defined tasks requiring deterministic solutions. However, constructing systems that include simulated training partners is much harder. Oftentimes, the tasks in these domains are not well-defined, there could be many probabilistic events, and the number of combinations of different actions can be huge. In order to be effective, the training partners need to show (1) varying levels of autonomy and (2) a broad range of complex, believable behavior, so that the human trainee can be engaged and can learn to cope with different kinds of situations. Thus, autonomy and complex, believable behavior are the two main issues for simulated training partners. In this report, we will review dif-1 ferent types of simulated training partners, followed by an in-depth discussion on autonomy and complex, believable behavior generation, and recommendations on optimal combination

In this paper, we will review a novel microscopy modality called Knife-Edge Scanning Microscopy (KESM) that we have developed over the past twelve years (since 1999) and discuss its relevance to connectomics and neural networks research. The operational principle of KESM is to simultaneously section and image small animal brains embedded in hard polymer resin so that a near-isotropic, sub-micrometer voxel size of 0.6 µm × 0.7 µm × 1.0 µm can be achieved over ∼1 cm 3 volume of tissue which is enough to hold an entire mouse brain. At this resolution, morphological details such as dendrites, dendritic spines, and axons are visible (for sparse stains like Golgi). KESM has been successfully used to scan whole mouse brains stained in Golgi (neuronal morphology), Nissl (somata), and India ink (vasculature), providing unprecedented insights into the system-level architectural layout of microstructures within the mouse brain. In this paper, we will present whole-brain-scale data sets from KESM and discuss challenges and opportunities posed to connectomics and neural networks research by such detailed yet system-level data. I.

When a new-born animal (agent) opens its eyes, what it sees is a patchwork of light and dark patterns, the natural scene. What is perceived by the agent at this moment is based on the pattern of neural spikes in its brain. Life-long learning begins with such a flood of spikes in the brain. All knowledge and skills learned by the agent are mediated by such spikes, thus it is critical to understand what information these spikes convey and how they can be used to generate meaningful behavior. Here, we consider how agents can autonomously understand the meaning of these spikes without direct reference to the stimulus. We find that this problem, the problem of grounding, is unsolvable if the agent is passively perceiving, and that it can be solved only through selfinitiated action. Furthermore, we show that a simple criterion, combined with standard reinforcement learning, can help solve this problem. We will present simulation results and discuss the implications of these results on life-long learning.

Abstract—We investigate how an autonomous humanoid robot with an initially inaccurate binocular vision system can learn to correct inconsistencies in its understanding of distance using information and resources that might be available to a human infant. We defined a consistent depth estimator as a Euclidean distance metric where the unit of measurement is determined autonomously. We found that an error signal that exploits actions that maintain invariant distance is a powerful tool for correcting inconsistency. Our results show that a heuristic search algorithm, run incrementally as new data become available, can efficiently (i.e. with few samples) correct inconsistencies and improve depth estimates.