We present a short survey of ways in which existing scientific knowledge are included when constructing models with neural networks . The inclusion of domain-knowledge is of special interest not just to constructing scientificassistants, but also, many other areas that involve understanding data using human-machine collaboration . In many such instances, machine-based model construction may benefit significantly from being provided with human-knowledge encoded in a sufficiently precise form . In each category, we describe techniques that have been shown toyield significant changes in network performance . In practice we expect a combination of such changes to: the input, the loss function, and the architecture of deep networks .

Author(s) : Tirtharaj Dash, Sharad Chitlangia, Aditya Ahuja, Ashwin Srinivasan

Links : PDF - Abstract

Code :
Coursera

Keywords : knowledge - networks - - machine - human -

Leave a Reply

Your email address will not be published. Required fields are marked *