Robby is available for hire
Hire RobbyRobby Goetschalckx
Verified Expert in Engineering
Artificial Intelligence (AI) Developer
Location
Eugene, OR, United States
Toptal Member Since
December 12, 2017
Robby is a machine learning expert with 10+ years of experience in research and back-end software development for machine learning solutions. With master's degrees in computer science and artificial intelligence in addition to his Ph.D. in computer science, Robby is well equipped to provide solutions to a variety of issues in companies of all sizes.
Portfolio
Eduworks Corporation
Natural Language Understanding (NLU), CSV, SciPy...
Connected Signals
Jupyter Notebook, CSV, SciPy, Matplotlib, Bayesian Statistics, Research...
Eduworks Corporation
Natural Language Understanding (NLU), Functional Programming, CSV, SciPy, GPT...
Experience
Availability
Part-time
Preferred Environment
SciPy, Linux, Python 3, Django, Pandas
The most amazing...
...system I worked on was a fully automatic robotic device for post-stroke rehab. My part was the automatic decision making about optimal difficulty of exercise.
Work Experience
Machine Learning Researcher (Contract)
2017 - PRESENT
Eduworks Corporation
- Created a tractable algorithm to infer skill mastery in complex competency frameworks from potentially conflicting sources of information.
- Performed experiments with an algorithm on simulated data to validate the correctness and significance of improvement over baseline.
- Wrote a white paper on inference in complex competency frameworks.
Technologies: Natural Language Understanding (NLU), CSV, SciPy, Natural Language Processing (NLP), GPT, Generative Pre-trained Transformers (GPT), Matplotlib, Bayesian Statistics, Research, Bayesian Inference & Modeling, Probability Theory, Git, NumPy, Python, Python 2, Python 3, Probabilistic Graphical Models, Machine Learning, Artificial Intelligence (AI), Java
Senior Software Engineer
2017 - 2020
Connected Signals
- Provided prediction models for bus ETAs at traffic lights for signal priority requests.
- Created a prediction model for response delay for drivers at a traffic light turning from red to green.
- Created prediction models for traffic lights from vehicular probe data (GPS traces).
Technologies: Jupyter Notebook, CSV, SciPy, Matplotlib, Bayesian Statistics, Research, Bayesian Inference & Modeling, Probability Theory, Git, Linux, Data Science, Scikit-learn, NumPy, Python, Python 3, Machine Learning, Artificial Intelligence (AI), Pandas
Software Developer and Machine Learning Expert
2016 - 2017
Eduworks Corporation
- Created a fully automated multiple-choice quiz generation system, which takes in a text document, identifies keywords, and generates questions.
- Developed a system to perform inference in complex competency frameworks, parsing (potentially conflicting) evidence from various sources.
- Built a machine learning system to detect voice phishing attacks from audio signals, by detecting various types of tampering (splicing, synthetic voices, and replay attacks).
- Developed several ideas for potential project proposals, involving machine learning, natural language processing, and automatic decision making.
Technologies: Natural Language Understanding (NLU), Functional Programming, CSV, SciPy, Generative Pre-trained Transformers (GPT), GPT, Natural Language Processing (NLP), Matplotlib, Bayesian Statistics, Research, Bayesian Inference & Modeling, Probability Theory, Git, Agile Software Development, Java 8, NumPy, Python, Python 2, Python 3, Probabilistic Graphical Models, Machine Learning, Artificial Intelligence (AI), Apache Maven, Java
Postdoctoral Researcher
2012 - 2015
Oregon State University
- Created various algorithms for learning in an interactive loop between a (human) subject matter expert and an AI system.
- Designed various algorithms for imitation learning—a machine learning system that takes in expert solutions and tries to learn the underlying policy.
- Developed a system to perform path planning for multiple agents for a complex search and coverage problem.
- Created an algorithm to perform inference in MOOC frameworks by predicting readiness-to-learn using Bayesian techniques.
- Designed algorithms for multi-task classification, by exploiting task descriptions and balancing specification and generalization.
Technologies: CSV, SciPy, Matplotlib, Reinforcement Learning, Bayesian Statistics, Research, Bayesian Inference & Modeling, Probability Theory, Linux, NumPy, Python, Python 2, Python 3, Probabilistic Graphical Models, Machine Learning, Artificial Intelligence (AI)
Postdoctoral Researcher
2011 - 2012
University of Waterloo
- Developed algorithms to perform inference on a discrete output variable with a continuous input space.
- Built a system to perform inference and planning in a complex system to assist in post-stroke rehabilitation.
Technologies: CSV, SciPy, Matplotlib, Reinforcement Learning, Bayesian Statistics, Research, Bayesian Inference & Modeling, Probability Theory, NumPy, Python, Python 2, Python 3, Probabilistic Graphical Models, Machine Learning, Artificial Intelligence (AI)
Experience
Question Generation
http://eduworks.com/assessment-generation.htmlAutomated quiz generation from text documents. Identifying keywords, creating questions and distractors for multiple-choice questions, and choosing high-quality questions with high relevance for the subject matter.
Intelligent Post-stroke Rehab Robot
Automatic robot to assist people in post-stroke exercises for upper limbs. The robot acts as a controller for a video game, where physical resistance level and target distance can be set automatically. The system keeps a belief state of the person's physical capabilities and fatigue level, and makes decisions accordingly, even deciding when to tell the person to take a break.
Bus ETAs for Signal Priority Requests
Based on GPS traces of bus routes, I created predictive models of when a bus would arrive at a signalized intersection. This allows the system to request traffic light changes or delays. At the test city, the result was that buses only had to stop at traffic lights 60% as often as before; wait times for red lights were greatly reduced.
Skills
Languages
Python, Python 2, Python 3, Prolog, Java 8, Java, C++
Libraries/APIs
NumPy, SciPy, Matplotlib, Pandas, Scikit-learn
Tools
Jupyter, Apache Maven, Git
Paradigms
Data Science, Agile Software Development, Functional Programming, Declarative Programming
Platforms
Jupyter Notebook, Linux
Other
Research, Bayesian Statistics, Reinforcement Learning, Machine Learning, Artificial Intelligence (AI), Probabilistic Graphical Models, Probability Theory, Bayesian Inference & Modeling, Natural Language Processing (NLP), CSV, GPT, Generative Pre-trained Transformers (GPT), Natural Language Understanding (NLU)
Frameworks
Django
Storage
SQLite
Education
2004 - 2009
Ph.D. in Computer Science
Katholieke Universiteit Leuven - Leuven, Belgium
2003 - 2004
Advanced Master's Degree in Artificial Intelligence
Katholieke Universiteit Leuven - Leuven, Belgium
1999 - 2003
Master's Degree in Computer Science
Katholieke Universiteit Leuven - Leuven, Belgium
Collaboration That Works
How to Work with Toptal
Toptal matches you directly with global industry experts from our network in hours—not weeks or months.
1
Share your needs
Discuss your requirements and refine your scope in a call with a Toptal domain expert.
2
Choose your talent
Get a short list of expertly matched talent within 24 hours to review, interview, and choose from.
3
Start your risk-free talent trial
Work with your chosen talent on a trial basis for up to two weeks. Pay only if you decide to hire them.
Top talent is in high demand.
Start hiring