Heather Couture, Phd Email and Phone Number
Heather Couture, Phd work email
- Valid
- Valid
Heather Couture, Phd personal email
Are you frustrated by the never ending cycle of machine learning experiments?• Do your models perform well on your training data but fail on images from a different source?• Does your team struggle to keep up with the rapidly advancing field?• Are you unsure whether you’re focusing on the best model types for your application?• Do you have data challenges like multispectral images, noisy labels, or small training sets?Get to market faster with less wasted time on unsuccessful approaches• Build robust and generalizable models• Stay up-to-date with the latest and greatest tools and techniques• Follow best practices for your unique data challenges• Develop unbiased models that produce the most valuable insightsI guide startups to reduce the trial-and-error of machine learning model development by:• Identifying sources of variation or domain shifts• Understanding prior work with a literature review• Validating early and often to reveal failure modesTo learn more:Consulting services: http://pixelscientia.comEmail: heather@pixelscientia.comImpact AI Podcast: https://pixelscientia.com/podcastComputer Vision Insights Newsletter: https://pixelscientia.com/newsletterAbout me:• 20 years’ experience in academia and industry• PhD in Computer Science• 15+ peer-reviewed publications including CVPR, NeurIPS, MICCAI, and NPJ Breast Cancer• 3 patents granted, 1 pending• Led WattTime’s ML efforts to estimate GHG emissions from sources on Earth using satellite imagery in support of their mission with Climate TRACE• Collaborated with a team at the University of North Carolina to study prognostic and predictive properties of breast tumors from H&E histology that can lead to improved treatment decisions; created a method to predict cancer biomarkers too complex for pathologists to see• Led Digitalsmiths’ (since acquired by TiVo) R&D team to create software for indexing and retrieval of movies and TV shows• Worked with the Mars Space Flight Facility at Arizona State University to detect rocks in high-resolution satellite imagery of Mars and create rock distribution maps for selecting a landing site for the Phoenix Lander• In the Robotics Institute at Carnegie Mellon University created new methods to detect, segment, and geologically classify rocks on Mars for autonomous science
Pixel Scientia Labs, Llc
View-
Founder & Computer Vision ConsultantPixel Scientia Labs, Llc Oct 2012 - PresentConsultant to startups using computer vision and machine learning.How I reduce the trial-and-error of machine learning development:• Facilitate knowledge sharing amongst stakeholders, domain experts, and engineers• Guide machine learning engineers to the most effective models and experiments• Handle the challenges of real world data• Follow industry best practices• Create a clear project roadmap• Design generalizable models• Properly validate models• Smoothly navigate through challenges• Help you build an interdisciplinary teamSample projects:• Estimate GHG emissions from power plants using satellite imagery• Detect rocks and craters on Mars from satellite imagery• Correlate multispectral with H&E images to detect cancer• Biomarker prediction from tumor histology using deep learning• Identify artifacts in whole slide images• Create models that generalize to other scanners and labs• Detect mitoses in whole slide images• Count, segment, and classify cells in high resolution images• 3D segmentation of human and mouse retina layers from optical coherence tomography
-
Computer Vision InsightsPixel Scientia Labs, Llc Feb 2021 - PresentA newsletter to bring the latest machine learning and computer vision research to applications in people and planetary health.
-
Podcast HostPixel Scientia Labs, Llc Oct 2022 - PresentLearn how to build a mission-driven machine learning company from the innovators and entrepreneurs who are leading the way. A weekly show about the intersection of ML and business – particularly startups. We discuss the challenges and best practices for working with data, mitigating bias, dealing with regulatory processes, collaborating across disciplines, recruiting and onboarding, maximizing impact, and more.
-
Research AssistantUniversity Of North Carolina At Chapel Hill Aug 2012 - Dec 2018Chapel Hill, Nc, Us• Created a hierarchical task-driven dictionary learning method for classifying H&E images (published at ISBI).• Developed a method to predict molecular tumor biomarkers from H&E - properties that are too complex for a pathologist to assess visually (published in NPJ Breast Cancer, patent pending).• Created a weakly supervised deep learning method to improve classification of heterogeneous tumors and provide insight into where the heterogeneity lies (published at MICCAI).• Integrated imaging and genomic data during training to improve classification when only one modality is available; created a new deep learning method that also improves state-of-the-art on benchmark multimodal data sets (under review).• Worked on a deep learning method to predict cancer recurrence from histology. -
Image Computational EngineerDigitalsmiths Apr 2007 - Aug 2012• Research and development of image/video indexing and retrieval using computer vision and machine learning techniques.• Evaluated new tools, prototyped algorithms, implemented product components.• Created metrics to quantify different aspects of an algorithm’s performance.• Collaborated with engineering teams to aid delivery of algorithms into production systems.• Communicate methods and results to management.• Projects included: – Scene classification of images and video (e.g., beach, forest, urban) - published at CVPR workshop, 3 patents granted – Face detection, tracking, and grouping – Shot and scene boundary detection – Clip retrieval using video signature
-
Research TechnicianMars Space Flight Facility, Arizona State University Oct 2006 - Feb 2007Tempe, Az, Us• Research and development of methods for the detection and size estimation of craters in thermal satellite images of Mars.• Developed a system to detect rocks in high-resolution Mars satellite imagery and created rock distribution maps for selecting a landing site for the Phoenix Lander. -
Research AssistantRobotics Institute, Carnegie Mellon University Jan 2006 - Aug 2006Pittsburgh, Pa, Us• Research, analysis, and development of methods for autonomous science.• Automatic detection and classification of rocks: detection of rocks with an accurately delineated boundary (published at CVPR), characterization of rock shape, geologic classification with color, texture, and shape features. -
Software Developer/TesterXiris Automation Inc. May 2004 - Aug 2004Burlington, Ontario, Ca• Development in a team on applications for Ident code verification and printed graphics inspection of optical discs.• Application testing, debugging, documentation. -
Software DeveloperDiscreet Logic Sep 2003 - Dec 2003• C++ development in a Unix environment on a high-performance visual effects package.• Integrated 3-D lookup table functionality into Flame.
-
Machine Vision ProgrammerAgris-Schoen Vision Systems Sep 2002 - Apr 2003• Assisted in software design process and wrote functional specifications.• Developed object-oriented software modules from design/functional specifications.• Evaluated signature matching algorithms.• Implemented machine vision feasibility studies on client samples sent for evaluation.
-
Software DeveloperAlias|Wavefront Jan 2002 - Apr 2002Us• Member of the Product Development Group for StudioTools, a 3-D graphics package for the design and styling of automotive and industrial products.• Developed C++ and Perl tools to largely automate the renovation of a large codebase. -
Software DeveloperSun Microsystems/Isopia Inc. May 2001 - Aug 2001Palo Alto, Ca, Us• Worked in a team to develop client-specific user interfaces for a web-based e-learning management system; coded in Java, JavaScript, JSP and HTML. -
ProgrammerIbm Aug 1999 - Aug 1999Armonk, New York, Ny, Us• “Editor-in-chief” of the Frequently Asked Questions database for VisualAge for C++.• Worked with the Build, Install and Packaging team for VisualAge for Java.
Heather Couture, Phd Skills
Heather Couture, Phd Education Details
-
University Of North Carolina At Chapel HillComputer Science -
Carnegie Mellon UniversityRobotics
-
University Of WaterlooComputer Science
Frequently Asked Questions about Heather Couture, Phd
What company does Heather Couture, Phd work for?
Heather Couture, Phd works for Pixel Scientia Labs, Llc
What is Heather Couture, Phd's role at the current company?
Heather Couture, Phd's current role is Fighting Cancer and Climate Change with AI • Consultant, Researcher, Writer & Host of Impact AI Podcast.
What is Heather Couture, Phd's email address?
Heather Couture, Phd's email address is he****@****op1.net
What schools did Heather Couture, Phd attend?
Heather Couture, Phd attended University Of North Carolina At Chapel Hill, Carnegie Mellon University, University Of Waterloo.
What skills is Heather Couture, Phd known for?
Heather Couture, Phd has skills like Machine Learning, Algorithms, Computer Vision, Python, Matlab, C++, Machine Vision, Image Processing, Software Development, Medical Image Analysis, Image Analysis, Pattern Recognition.
Free Chrome Extension
Find emails, phones & company data instantly
Aero Online
Your AI prospecting assistant
Select data to include:
0 records × $0.02 per record
Download 750 million emails and 100 million phone numbers
Access emails and phone numbers of over 750 million business users. Instantly download verified profiles using 20+ filters, including location, job title, company, function, and industry.
Start your free trial