Robin Yancey Machine Learning Engineer
No reviews yet

Hi! My name is Robin. I have PhD and MS graduate degrees in Computer Science and Electrical Engineering from UC Davis, where I was employed as the full instructor for the undergraduate Machine Learning Course. I was then employed as Machine Learning PostDoc at LLNL where I worked on the NIF during the recent world breakthrough where we achieved nuclear fusion. Throughout my university and postdoc research I not only published dozens of papers, but also developed many frameworks in the fields of Machine Learning, Deep Learning, Computer Vision, and Data Science.

I mainly offer 3 different series of lessons (Python, ML, and DL). Below is a list of examples of things I cover in each. Not everything is included here so feel free to ask me if there is something specific you'd like to learn as well.

Machine Learning:
- KNN, Decision Trees (including random forest, bagging, boosting), PCA, SVM, Linear and Polynomial Models (including GLM), Neural Networks (all both code in sklearn and mathematical theory)
- Prepare data for ML using Pandas (handle NAs, missing values, data type issues etc.)
- Core concepts: classification/regression, dimensionality reduction, over/under-fitting, k-fold testing, proper results/accuracy presentation, parallelization, hyper-parameter optimization, class imbalance, scaling and handling outliers

Deep Learning:
- How to both apply and optimize DL models (eg. in PyTorch, Tensorflow, Keras, Scikit-Learn)
- Build full train/test/eval frameworks
- Understand and learn how to choose loss functions, optimizers, and other DL hyperparameters
- Transfer Learning (and how to retrain or fine tune off-the-shelf top models for other tasks)
- Transformers architecture breakdown and how to implement in code (eg. ViT, Swin, HuggingFace models etc.)
- OpenCV and and top Computer Vision models architecture in depth (including image classification and object detection)
- Intro to NLP
- GPU training, handling large tensor data, many ways of handling class imbalance
- Data transformations and augmentation
- Results analysis/reporting/plotting

Python:
Basics (functions, If-else, lists, tuples, dicts, classes, etc.)
LeetCode problems and Interview prep (Ive solved hundreds)
Advanced Data Structures and Algorithms (eg. Trees, Linked Lists, time-complexity, sorting)

Subjects

Python Beginner-Intermediate
Deep Learning Beginner-Intermediate
Computer Vision Beginner-Intermediate
Machine learning Python Beginner-Intermediate

Experience

Machine Learning PostDoc (Sep, 2022–Present) at Lawrence Livermore National Labs
Course Instructor (Machine Learning) (Mar, 2020–Aug, 2020) at UC Davis Dept. of Computer Science

• Spring Quarter 2020; Enrollment 100 Students.
• Summer Quarter 2020; Enrollment 150 Students.
• Taught all theory & Python implementation of: Regression, Classification, Large Data, Decision Trees, Bagging/Boosting,
Random Forest, GLM/LM, SVM, CNN/DNN, Object Detection Applications (see ECS 171 Syllabus)
• Created all of my own original course materials, see: Notes, Homework, Quizzes (re-used by the next Professor)
Research & Teaching Assistant (Jan, 2017–Jan, 2021) at UC Davis Dept. of Computer Science

As an RA I published dozens of papers in Deep Learning, Computer Vision, Machine Learning, and statistics

Each TA position included 20 hr/week of: leading full weekly 1-4 hour discussion or lab sessions of 50+ students, creating rubrics/solutions/grades for homework & quizzes, and holding office hours for lecture questions

Education

PhD (Jun, 2016–Jan, 2022) from University of California, Davis–scored 3.8
Masters (Jun, 2016–Jun, 2018) from University of California, Davis–scored 3.8

Fee details

US$35–50/hour (US$35–50/hour)

May go up slightly when more experience on website is recorded.

Courses offered

Machine Learning
- US$70
- Duration: 15 hours
- Delivery mode: Online
- Group size: Individual
- Instruction language: English
- Certificate provided: Yes
- KNN, Decision Trees (including random forest, bagging, boosting), PCA, SVM, Linear and Polynomial Models (including GLM), Neural Networks (all both code in sklearn and mathematical theory)
- Prepare data for ML using Pandas (handle NAs, missing values, data type issues etc.)
- Core concepts: classification/regression, dimensionality reduction, over/under-fitting, k-fold testing, proper results/accuracy presentation, parallelization, hyper-parameter optimization, class imbalance, scaling and handling outliers
Deep Learning
- US$70
- Duration: 15 hours
- Delivery mode: Online
- Group size: Individual
- Instruction language: English
- Certificate provided: Yes
- How to both apply and optimize DL models (eg. in PyTorch, Tensorflow, Keras, Scikit-Learn)
- Build full train/test/eval frameworks
- Understand and learn how to choose loss functions, optimizers, and other DL hyperparameters
- Transfer Learning (and how to retrain or fine tune off-the-shelf top models for other tasks)
- Transformers architecture breakdown and how to implement in code (eg. ViT, Swin, HuggingFace models etc.)
- OpenCV and and top Computer Vision models architecture in depth (including image classification and object detection)
- Intro to NLP
- GPU training, handling large tensor data, many ways of handling class imbalance
- Data transformations and augmentation
- Results analysis/reporting/plotting
Python
- US$70
- Duration: 15 hours
- Delivery mode: Online
- Group size: Individual
- Instruction language: English
- Certificate provided: Yes
Basics (functions, If-else, lists, tuples, dicts, classes, etc.)
LeetCode problems and Interview prep (Ive solved hundreds)
Advanced Data Structures and Algorithms (eg. Trees, Linked Lists, time-complexity, sorting)