Neurons produce action potentials or spikes in response to a wide variety of inputs. Correlations between interspike intervals are often seen in data from single neurons, and are due to a combination of intrinsic mechanisms and the temporal properties of the input stimulus. Here we review recent progress in our understanding of how intrinsic correlations arise in simple biophysically justified ...

We introduce a learning framework called learning using privileged information (LUPI) to the computer vision field. We focus on the prototypical computer vision problem of teaching computers to recognize objects in images. We want the computers to be able to learn faster at the expense of providing extra information during training time. As additional information about the image data, we look a...

Most existing learning to hash methods assume that there are sufficient data, either labeled or unlabeled, on the domain of interest (i.e., the target domain) for training. However, this assumption cannot be satisfied in some real-world applications. To address this data sparsity issue in hashing, inspired by transfer learning, we propose a new framework named Transfer Hashing with Privileged I...

In the study of complex systems a fundamental issue is the mapping of the networks of interaction between constituent subsystems of a complex system or between multiple complex systems. Such networks define the web of dependencies and patterns of continuous and dynamic coupling between the system's elements characterized by directed flow of information spanning multiple spatial and temporal sca...

This paper examines the methods for exploring volume data by optimization of visualization parameters. The size and complexity of the parameter space controlling the rendering process makes it challenging to generate an informative rendering. In particular, the specification of the transfer function (which is a mapping from data values to visual properties) is frequently a time-consuming and un...

A somewhat controversial but continuing trend among large divisionalized corporations is to centralize the provision of information system services in the MIS department. The objectives of centralizing all or most MIS activities are to. obtain economies of scale in the acquisition of computer hardware and to eliminate duplicate system development 191. The centralization of MIS functions, howeve...