Wolfgang Black, PhD

Wolfgang Black, PhD

San Francisco, California, United States
952 followers 500+ connections

About

Applied scientist in Machine learning classically trained in Mechanical Engineering with…

Activity

Join now to see all activity

Experience

  • Civitai Graphic

    Civitai

    San Francisco, California, United States

  • -

    San Francisco Bay Area

  • -

    San Francisco Bay Area

  • -

  • -

    Livermore, California

  • -

    Los Alamos, NM

  • -

  • -

  • -

  • -

    Columbia, Missouri

  • -

Education

  • University of Missouri-Columbia Graphic
  • -

    - Developed end-to-end modeling pipelines to tackle object detection, semi-supervised learning for biomedical image classification, and conversational AI utilizing SOTA deep learning

    - Deployed models on AWS utilizing Docker and EC2 instances

  • -

    Activities and Societies: Teaching assistant for Solid Modelling, Thermodynamics Research assistant for the Missouri Shock Tube Facility

  • -

Licenses & Certifications

Courses

  • Advanced Thermodynamics

    8380

  • Computational Heat Transfer and Fluid Dynamics

    8420

  • Gas Dynamics

    7450

  • Intermediate Fluid Mechanics

    7420

  • Intermediate Heat Transfer

    7310

  • Introduction to Turbulence

    8450

  • Introduction to Two-Phase Flow

    8430

Projects

  • Contrastive Learning for OCT Disease Classification

    -

    Retinal OCT image analysis for eye disease diagnosis: The OCT (Optical Coherence Tomography) is an imaging method used to capture cross sections of the retinas of patients. The captured images are used to diagnose the patient’s retinal health into four categories: Normal, CNV, DME, and DRUSEN. The goal of the first part of the project is to reproduce the state of art classification accuracy by training Deep Convolution Networks following the standard Supervised Learning paradigm. The second…

    Retinal OCT image analysis for eye disease diagnosis: The OCT (Optical Coherence Tomography) is an imaging method used to capture cross sections of the retinas of patients. The captured images are used to diagnose the patient’s retinal health into four categories: Normal, CNV, DME, and DRUSEN. The goal of the first part of the project is to reproduce the state of art classification accuracy by training Deep Convolution Networks following the standard Supervised Learning paradigm. The second part of the project is about learning features from images without labels (Unsupervised Learning) based on the recent ‘Self-Supervised Learning’ method, with the goal of improving the classification accuracy over the baseline established from the first part of the project.

    Other creators
    See project

Languages

  • Japanese

    Limited working proficiency

  • German

    Limited working proficiency

  • English

    Native or bilingual proficiency

Recommendations received

2 people have recommended Wolfgang

Join now to view

More activity by Wolfgang

View Wolfgang’s full profile

  • See who you know in common
  • Get introduced
  • Contact Wolfgang directly
Join to view full profile

Other similar profiles

Explore collaborative articles

We’re unlocking community knowledge in a new way. Experts add insights directly into each article, started with the help of AI.

Explore More

Add new skills with these courses