Machine learning projects strive to create an impact, but there is often not a clear path to get there.

Navigating a successful project requires expertise in this highly technical field, up-to-date knowledge of research advances and toolkits, and a solid understanding of the data.

But there are unique intricacies when working with pathology and remote sensing data and in collaborating with the interdisciplinary teams involved. It takes many years to build the knowledge to be both efficient and effective in solving problems in these domains.

I help clients navigate these challenges by focusing on 7 key components:

  • Clarity on available data and prediction task
  • Review of related work to guide expectations
  • Metrics that capture project objectives and measure progress in modeling
  • Data pipeline for labeling, preprocessing, and cleaning
  • Model selection, implementation, and optimization
  • Model validation, error analysis, and understanding of implications
  • Successive iterations of the above components to generate new insights

My service offerings help clients to understand these key areas and advance in each to maximize the impact of their project.

How: Join weekly team meetings or planning sessions to provide feedback, suggestions, and links to helpful resources


  • Join weekly team meetings
  • Be available by email or scheduled phone call to answer questions
  • Provide reference to relevant articles, existing libraries, and data sets
  • Advise on data requirements
  • Provide suggestions of types of models to try and experiments to run
  • Suggest error analysis techniques to guide data cleaning strategies or model improvements


  • Expert guidance for your in-house technical team
  • Insights that your team can take action on to improve your model
  • A smoother path to project success

How: Take a deeper dive into a particular aspect of the project to guide a specific need or address problems that arise

Includes all of Advisor plus:

  • Additional responsibilities set each week or month that may include:
  • Meeting with individual team members to work through a specific concern
  • Reviewing academic research to find candidate solutions for a problem
  • Assessing image and label quality to determine cleaning needs
  • Reviewing images to identify specific challenges or unique opportunities for modeling
  • Working with team members to develop and debug a model
  • Prototyping a new model
  • Reviewing results
  • Considering effects of model including unintended bias, generalizability, and interpretability
  • Assisting in hiring process for new ML team members


  • Implementation of model improvements by an experienced practitioner
  • Access to the latest advances in ML
  • Smoother navigation once unique challenges are realized and a novel solution is required

How: Lead the machine learning development for your team. I only provide this exclusive level of support to one client at a time

Includes all of Collaborator plus:

  • Integrate with your team on a daily basis to lead the machine learning direction of the project
  • Guide project goals and metrics of success
  • Help determine data infrastructure requirements to properly preprocess data for effective model training
  • Create, experiment with, and analyze models
  • Develop custom model for unique situations
  • Understand model mechanics and results in order to assess implications
  • Determine what additional resources are needed for success
  • Train team members
  • Communicate project status to stakeholders within company


  • Help with project planning, selection and implementation of models, running experiments, communicating results, and more
  • A head start in creating appropriate models and analyzing early results to guide the next steps, even before a full team has been established

Additional services:

  • Proof of concepts
  • Subject matter expert for grant proposals

Contact me to discuss your individual needs.

Don’t Outsource, Insource - and Empower Your Team

While machine learning certainly can bring new insights, precision, and efficiency, it takes time to build the technology to do it. And the path to a successful solution is generally not linear.

Many companies outsource machine learning projects. While this can be successful for well-defined applications with a limited scope, high impact projects are different. These projects are often part of a company’s core technology, so they prefer to keep the intellectual property development in house. But they may not have navigated the unique complexities of a machine learning project before. I can help you build the technology and your team in house, ensuring a smoother path to success.

My goal is not just to get you to an ideal solution but to ensure your team also understands how it works so that they can modify it and adapt to new challenges that arise. I will be there to help you navigate these obstacles as needed, but I consider my role most successful if I have transferred this knowledge to your team.


I do 95% of my work remote - and have been doing so for the past 8 years - using video conferencing, document sharing, cloud computing. All the tools are readily available, and I can adapt to a particular suite already in use by your team.

Technical Expertise

Image Analysis:

feature extraction

Computer Vision:

scene & object classification
feature learning

Machine Learning:

dimensionality reduction
multiple instance learning
performance analysis

Deep Learning:

convolutional neural networks
time-to-event analysis
transfer learning



Build an Interdisciplinary Team

I’ve worked with teams spanning many different disciplines and the best results tend to come from a combination of

  • Pathologists, remote sensing scientists, or other domain experts who understand the data and how it is collected,
  • Data scientists who gather and analyze it further,
  • Machine learning engineers who train and analyze models, and
  • Software engineers who bring all the pieces together and create a robust system.

Due to the interdisciplinary nature of teams, communication is key.

I can help you in building this team. We start by setting reasonable goals for the project and determine the resources needed. From initial models, we then assess possible next steps including gathering and labeling more data, cleaning data, extending models, and improving computational efficiency. More resources (human or computer) may be needed as the project progresses.