ePrints.FRI - University of Ljubljana, Faculty of Computer and Information Science

Operational Calculus on Programming Spaces

Žiga Sajovic (2017) Operational Calculus on Programming Spaces. Prešeren awards for students.

[img]
Preview
PDF
Download (475Kb)

    Abstract

    In this work we develop an algebraic language that represents a formal calculus for deep learning and is, at the same time a model which enables implementations and investigations of programs. To this purpose, we develop an abstract computational model of automat- ically di�erentiable programs. In the model, programs are elements of op. cit. programming spaces. Programs are viewed as maps from a �nite-dimensional vector space to itself op. cit. virtual memory space. Virtual memory space is an algebra of programs, an algebraic data structure (one can calculate with). The elements of the virtual memory space give the expansion of a program into an in�nite tensor series. We de�ne a di�erential operator on programming spaces and, using its powers, implement the general shift operator and the operator of program composition. The algebraic language constructed in this way is a complete model of deep learning. It enables us to express programs in such

    Item Type: Thesis (Prešeren awards for students)
    Keywords: operator algebra, tensor algebra, neural networks, deep learning, automatic differentiation.
    Number of Pages: 54
    Language of Content: Slovenian
    Mentor / Comentors:
    Name and SurnameIDFunction
    prof. dr. Borut Robič28Mentor
    Link to COBISS: http://www.cobiss.si/scripts/cobiss?command=search&base=51012&select=(ID=1537658307)
    Institution: University of Ljubljana
    Department: Faculty of Computer and Information Science
    Item ID: 4022
    Date Deposited: 05 Dec 2017 09:58
    Last Modified: 06 Dec 2017 10:26
    URI: http://eprints.fri.uni-lj.si/id/eprint/4022

    Actions (login required)

    View Item