Skip to main content
  • Main Menu
  • Utility Menu
  • Search
University Logo
HARVARD.EDU

Allen Schmaltz

Contact

Allen Schmaltz
Shield
  • Bio
  • Contact
  • Research
  • Recent Talks
  • Upcoming Talks
  • Blog
  •  

     

    Since completing my Ph.D. in 2019 in Computer Science at Harvard, I have been working in the Department of Epidemiology to bring deep learning research to the Harvard medical community, and the medical field, more broadly. Toward this end, I have developed a series of new approaches for understanding, analyzing, and updating neural networks and their associated datasets.

    I have uploaded some recent presentation materials that provide an overview of my current line of research, and the images included at the bottom of this page (or here as a single PDF) summarize the key aspects.

     

    Curriculum Vitae

     

    Uncertainty is but a distance to what is known...

     

    Visual Research Overview:

    Deep Networks as Metric Learners

    Model Decompositions

    Prediction Reliability Heuristics

    Exemplar Auditing Lifecycle

    Out-of-Domain Settings

    Exemplar Auditing Implementations

    Memory Matching Search

    Retrieval-Classification via a Coarse-to-Fine Search

    Joint Training

    Multi-Sequence Representation Composition

    Token-Level Representations

    Comparative Feature-wise Summarization

    Multi-Task Future

Admin Login
OpenScholar
Copyright © 2022 The President and Fellows of Harvard College | Privacy | Accessibility | Digital Accessibility | Report Copyright Infringement