Principal Software Development Engineer, Artificial Intelligence
2021 - 2021Traptic- Led the development of the robot's visual system software using deep learning and computer vision, including coding in Python and Bash for training, tuning, and deploying to the production of customized convolutional neural network architectures.
- Contributed to the architectural modifications and custom loss functions for the neural networks that allowed the inference of multiple targets from images with semi-supervised training.
- Championed the delivery of a mathematical model of harvest yield that allowed tuning aspects of the visual and robotics systems to maximize the robot's strawberry picking rate.
Technologies: Computer Vision, Deep Learning, Python, Machine Learning, Algorithms, Artificial Intelligence (AI), Convolutional Neural NetworksSenior Machine Learning Engineer
2017 - 2019SAIC Innovation Center- Developed a driver monitoring system fusing video and biometric streams.
- Built a system to predict a driver's intended destination.
- Developed a system to anticipate drivers' environmental control preferences.
Technologies: Amazon Web Services (AWS), OpenCV, TensorFlow, Python, Computer Vision, PyTorch, Deep Learning, Algorithms, JSON, Artificial Intelligence (AI), Convolutional Neural NetworksSenior Data Scientist
2015 - 2017Venafi- Developed an anomaly detection system for PKI certificates using Spark and Python.
- Developed software to organize customers' internal PKI certificates into functionally meaningful groups with hierarchical clustering and a customized domain name similarity metric. Built a stand-alone REST API for this back end using Flask.
- Developed a system to assign a score to certificates on the basis of revocation likelihood as estimated with machine learning.
Technologies: MLlib, Linux, Unix, Amazon EC2, Amazon S3 (AWS S3), RStudio Shiny, R, Flask, Scikit-learn, Spark, Python, Deep Learning, Algorithms, JSON, Artificial Intelligence (AI), Convolutional Neural NetworksSenior Research Scientist I
2008 - 2010Pfizer- Developed a machine learning system for the prediction of antibody thermal and acidic stability on the basis of primary sequence with the aim of identifying stability improving inducible mutations.
- Identified common biological activity among a large panel of compounds with unsupervised learning and computer vision applied to digital microscopy.
- Performed text mining and natural language processing of a large corpus of miRNA-related publications.
Technologies: MATLAB, R, Statistics, Machine Learning, Algorithms, Artificial Intelligence (AI)
Matthew Woods
Machine Learning Developer in San Jose, CA, United States
Member since December 21, 2020
For the past 12 years, Matthew has been creating applied machine learning and data-driven engineering projects in multiple industrial sectors including agriculture, biotechnology, cybersecurity, and automotive. He is passionate about developing technologies that exploit his knowledge and experience with machine learning.
Matthew is now available for hire
Portfolio
- TrapticComputer Vision, Deep Learning, Python, Machine Learning, Algorithms...
- SAIC Innovation CenterAmazon Web Services (AWS), OpenCV, TensorFlow, Python, Computer Vision...
- VenafiMLlib, Linux, Unix, Amazon EC2, Amazon S3 (AWS S3), RStudio Shiny, R, Flask...
Experience
- Mathematics 20 years
- Science 20 years
- Unsupervised Learning 17 years
- Supervised Learning 17 years
- Signal Processing 17 years
- Machine Learning 17 years
- Time Series 17 years
- Python 7 years
Availability
Full-time
Preferred Environment
Amazon Web Services (AWS), Trello, Git, PyCharm, Unix, MacOS
The most amazing...
...thing I have developed is a machine learning software that produced the first place winning models in the MAQC competition.
Employment
Experience
- Neural Network and Bioinformatic designs for Predicting HIV-1 Protease Inhibitor Resistance
Doctoral work.
I created a new machine learning method for online-learning of continuous-valued multi-dimensional to multi-dimensional maps, a novel feature selection method, and a general-purpose protein-encoding scheme for ML applications. These methods are used to personalize the treatment of HIV-positive patients.
Skills
Other
Machine Learning, Science, Statistics, Simulations, Supervised Learning, Unsupervised Learning, Time Series, Signal Processing, Mathematics, Algorithms, Modeling, Artificial Intelligence (AI), Differential Equations, Software Development, Sensor Fusion, Sensor Data, Deep Learning, Convolutional Neural Networks, Computer VisionLanguages
Python, RLibraries/APIs
TensorFlow, OpenCV, Keras, Scikit-learn, MLlib, PyTorchTools
PyCharm, Git, Trello, MATLABPlatforms
MacOS, Unix, Amazon Web Services (AWS), Amazon EC2, LinuxFrameworks
Spark, Flask, RStudio ShinyStorage
Amazon S3 (AWS S3), JSON
Education
- Ph.D. in Cognitive and Neural Systems2001 - 2007Boston University - Boston, MA, USA
- Bachelor's Degree in Physics and Mathematics1992 - 1996University of Michigan - Ann Arbor, MI, USA
