Skip to content
View johnHostetter's full-sized avatar

Block or report johnHostetter

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 250 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
johnHostetter/README.md

Hi there πŸ‘‹ I'm John

Github LinkedIn Github Stars Github Followers

About Me πŸ™‚

I am an Assistant Professor within the Department of Analytics and Information Systems at Western Kentucky University's Gordon Ford College of Business. My research experience revolves around neuro-symbolic architectures called neuro-fuzzy networks (NFNs).

Current Work πŸ”­

I am researching a new prototype NFN that can automatically reconfigure its knowledge base in response to its performance with respect to an objective function. These architectures natively handle missing data in the inputs and can easily transfer their knowledge to other models. The results of this novel work are reported in my dissertation.

Primary Accomplishments πŸ†

  • Created the first method to achieve fuzzy reinforcement learning in computer vision tasks (refer to my dissertation).
  • First publication to create NFNs for tasks with high dimensions (to the best of my knowledge). DOI:10.5555/3545946.3598770
  • Published the first work solely dedicated to offline model-free fuzzy reinforcement learning. DOI:10.5555/3545946.3598770
  • First work to use fuzzy logic control to yield a pedagogical policy. DOI:10.1109/FUZZ52849.2023.10309741

Q & A ❓

Can we collaborate on research?

I may be interested in a research collaboration. Please feel free to reach out.

What is my coding philosophy?

I implement a test-driven agile workflow that emphasizes modular and reusable code with high cohesion and low coupling. My code is clear, self-documenting, and minimal, yet I strongly advocate for comprehensive documentation, utilizing tools like Sphinx. I adhere to the relevant conventions of the programming language and maintain a consistent style, such as using Black for Python code formatting.

Contact Information πŸ“¬

Email: john.hostetter@wku.edu

Fun Fact ⚑

My "coding buddy" is an adopted four-year-old Siberian Husky named Zoey!

drawing

github stats for johnHostetter

Pinned Loading

  1. fuzzy-theory fuzzy-theory Public

    The fuzzy-theory library provides a PyTorch interface to fuzzy set theory and fuzzy logic operations.

    Python 1

  2. manim-timeline manim-timeline Public

    An animated timeline to seamlessly illustrate historical events, publications over time, and demos.

    Python 14 1

  3. manim-beamer manim-beamer Public

    A small repository containing my attempt to emulate the LaTeX beamer format within manim-slides.

    Python 13 1

  4. regime regime Public

    Create and visualize workflows consisting of classes, functions, and resources; recognize necessary hyperparameters.

    Python

  5. AAMAS-2023-FCQL AAMAS-2023-FCQL Public

    A systematic design process for a self-organizing neuro-fuzzy Q-network for model-free and offline reinforcement learning.

    Jupyter Notebook 9 2

  6. PolicyPrep PolicyPrep Public

    Prepares policies from data to model; focuses on hierarchical tasks and applies reward shaping to handle delayed reward signals.

    Python