Anti-DCN polyclonal antibody

We have trained deep convolutional neural networks (DCNs) to accelerate the computation of seismic attributes by an order of magnitude. These results are enabled by overcoming the prohibitive memory requirements typical of 3D DCNs for segmentation and regression by implementing a novel, memory-efficient 3D-to-2D convolutional architecture and by including tens of thousands of synthetically generated labeled examples to enhance DCN training. Including diverse synthetic labeled seismic in training helps the network generalize enabling it to accurately predict seismic attribute values on field-acquired seismic surveys. Once trained, our DCN tool generates attributes with no input parameters and no additional user guidance. The DCN attribute computations are virtually indistinguishable from conventionally computed attributes while computing up to 100 times faster.

Facing the exponential growth of the intra-datacenter traffic, the traditional Data-Center Network (DCN) architectures are not capable to stay ahead of the demand in terms of scalability and lowering costs. In this paper, we address the routing problem of the intra-datacenter traffic inside CamCube-based server-only DCNs. The latter are composed of servers only and no additional network equipments are employed. Following the SDN paradigm, we firstly propose a new architecture in which the control plane is hosted in an SDN controller. Next, we propose to emulate the whole DCN using the versatile "Mininet" platform. Then, we formulate the path computation problem, considering the Quality-of-Service (QoS) in terms of the requested bandwidth, as multi-objective combinatorial optimization problem. Next, we propose a thoughtful reformulation for the problem which can be solved using the Branch-and-Cut algorithm. Our proposal, named CamCube Routing Protocol (CRP), yields the optimal routing paths for the considered traffic flows that keep a balanced load on the DCN. Based on extensive emulations using "Mininet" and the "ONOS" SDN controller, the obtained results are very good, compared with the shortest-path approach, in terms of packet error rate and latency.