Software Engineering Institute | Carnegie Mellon University
Software Engineering Institute | Carnegie Mellon University

Digital Library

Javascript is currently disabled for your browser. For an optimal search experience, please enable javascript.

Advanced Search

Basic Search

Content Type

Topics

Publication Date

Presentation

Architectural Tradeoffs in Learning-Based Software

  • May 2018
  • By Pooyan Jamshidi (Carnegie Mellon University)518788
  • This presentation shows how architectural tradeoffs in learning-based software stacks are made via a case study of design space exploration in deep neural networks.
  • Publisher: Software Engineering Institute
  • This presentation was created for a conference series or symposium and does not necessarily reflect the positions and views of the Software Engineering Institute.
  • Abstract

    In classical software development, developers write explicit instructions in a programming language to hardcode the explicit behavior of software systems. By writing each line of code, the programmer instructs the software to have the desirable behavior by exploring a specific point in program space.

    Recently, however, software systems are adding learning components that, instead hardcoding an explicit behavior, learn a behavior through data. The learning-intensive software systems are written in terms of models and their parameters that need to be adjusted based on data. In learning-enabled systems, we specify some constraints on the behavior of a desirable program (e.g., a data set of input–output pairs of examples) and use the computational resources to search through the program space to find a program that satisfies the constraints. In neural networks, we restrict the search to a continuous subset of the program space.

    This talk provides experimental evidence of making tradeoffs for deep neural network models, using the Deep Neural Network Architecture system as a case study. Concrete experimental results are presented; also featured are additional case studies in big data (Storm, Cassandra), data analytics (configurable boosting algorithms), and robotics applications.

  • Download

Part of a Collection

SATURN 2018 Presentations