Machine learning and data analytics
Breakthrough machine learning capabilities
In today’s computing and networking environment, system complexity has grown to the point where it can no longer be handled manually by human experts. There is a pressing need for automation which takes the system environment into consideration to determine appropriate actions. In response, our researchers are developing cutting edge technologies that meet at the intersection of big data analytics, wireless networking and cybersecurity.
The key to our technology development efforts is our world-class research in new machine learning paradigms. We are creating advanced machine learning capabilities and applying them to an array of problems in networking, cybersecurity, sensor fusion, autonomy and financial analytics. In particular, our breakthrough machine learning paradigm, Learning Using Privileged Information (LUPI), mimics the process of human analysis to provide a variety of data analytics capabilities, including prediction and anomaly detection.
Essential capabilities for data analytics include scalable tools that validate, reconcile and store the data; ingenious algorithms that uncover patterns and trends; and end-to-end systems that extract key information. Perspecta Labs researchers are working on precisely these aspects of information analytics, including:
Video analytics: We are applying our breakthrough research paradigm, LUPI, to the detection of objects and activities in video of varying quality. Using LUPI, we can train models on high-resolution video and use these models to extract information of interest from low-resolution video at run time
Text analytics: Our researchers are developing capabilities that enable analysts to derive actionable intelligence from large, unknown and disparate sources of textual data. Capabilities include the ability to answer questions and provide supporting evidence
Financial analytics: We are applying our extensive capabilities in quantitative analytics to support the areas of capital markets and financial industry data analysis, as well as analytical development environment database support
Tool for data exploration and transformation: We have developed Arroyo, a forensic data analysis and transformation tool that scales up to the most demanding transaction volumes involving terabytes of data and billions of records. It is able to read data sources in many formats including unstructured text documents to extract named entities, events and relationships and to sort, classify, compare, transform and store the data in various ways
Mathematical data transformation: We have developed a new suite of fast algorithms that automatically represent high and/or multi-dimensional data at multiple scales and enable discovering patterns that cannot be detected otherwise