Convolutional neural networks (CNNs) are trained using stochastic gradient descent (SGD)-
based optimizers. Recently, the adaptive moment estimation (Adam) optimizer has become …

The IT industry is experiencing a disruptive trend for which the entire data center
infrastructure is becoming software defined and programmable. IT resources are …

Embodiments of the present invention provide an approach for adapting an information
extraction middleware for a clustered computing environment (eg, a cloud environ ment) by …

Enterprise data storage is usually designed to operate as a highly available system, which
needs continuous monitoring and diagnosing of a system state. However, applying the …

An enterprise storage system stores and gives access to valuable user data and hence is
required to operate as a highly available system. One of the key steps to desired reliability is …

6.389. 481 B1 5, 2002 Malcolm inferred semantics, extracts documentation from another
6438512 B 82002 Miller source code file. The extracted documentation and the 6,951,010 …

We introduce a parametric version (pDRUR) of the recently proposed Dimensionality
Reduction by Unsupervised Regression algorithm. pDRUR alternately minimizes …

The rapid proliferation of cloud and service-oriented computing infrastructure is creating an
ever increasing thirst for storage within data centers. Ideally management applications in …

In 2009, IBM launched its Smarter Planet™ initiative, which is based on the paradigm that
virtually any physical object, process, or system can be instrumented, interconnected, and …

Storage performance of a single virtual machine in a cloud computing environment may be
affected by other machines using the same physical storage. At the same time, user …