Uan Sholanbayev, Computer Vision Developer in Almaty, Kazakhstan
Uan Sholanbayev

Computer Vision Developer in Almaty, Kazakhstan

Member since October 11, 2019
After earning a degree in computer engineering from the University of California, San Diego, Uan has gained much in-depth and hands-on experience delivering services as a machine learning engineer. He is an expert in Python, deep learning, neural networks, and other AI algorithms. Uan is also an exemplary communicator and has worked in teams as well as individually.
Uan is now available for hire

Portfolio

  • G42
    PyTorch, Python 3, Solidity, You Only Look Once (YOLO), Game Theory...
  • MindsLenses
    Amazon Web Services (AWS), Deep Learning, Python, AWS, PyTorch, SQL...
  • Sportradar US
    Python

Experience

Location

Almaty, Kazakhstan

Availability

Part-time

Preferred Environment

GitLab, PyCharm, Ubuntu, MacOS, Amazon EC2 (Amazon Elastic Compute Cloud), MongoDB, Python 3, PyTorch, You Only Look Once (YOLO)

The most amazing...

...project I've worked on was an NFL drive prediction system based on neural networks. The predictions are used by betting companies to come up with coefficients.

Employment

  • Machine Learning Engineer

    2021 - PRESENT
    G42
    • Delivered a Computer Vision project to automatically read ID documents scans.
    • Developed Computer Vision software to detect road traffic violations.
    • Delivered a PCR registration chatbot, the basis was used to create other services later on.
    Technologies: PyTorch, Python 3, Solidity, You Only Look Once (YOLO), Game Theory, Computer Vision, Object Tracking, Chatbots, Rasa NLU, Moralis, Artificial Intelligence (AI), Ubuntu, Microsoft Excel, Jira, Agile Software Development, Machine Learning, Random Forests, Linear Regression, Logistic Regression, PyCharm, XGBoost, Scikit-learn, Sublime Text 3, Sublime Text, Video Processing, Image Processing
  • Computer Vision Developer

    2019 - 2020
    MindsLenses
    • Created a pipeline that processes everyday movies collected from RPI cameras. The processing includes several deep learning algorithms that detect human emotions in association with product interactions that are being handled in the store.
    • Trained deep learning models for object detection and classification. Utilized state-of-the-art frameworks to produce the best quality predictions.
    • Managed stable process of videos from raspberry pies to CV inference on the AWS cloud.
    Technologies: Amazon Web Services (AWS), Deep Learning, Python, AWS, PyTorch, SQL, PostgreSQL, Machine Learning
  • Machine Learning Engineer

    2017 - 2019
    Sportradar US
    • Created a neural network for the NFL to generate drive outcome predictions to further use from the betting companies.
    • Built NBA shot probability neural network models using Pytorch for fan experience enhancement.
    • Identified NBA events on games using tracking features with XGBoost.
    • Implemented an NBA data pipeline from different data sources.
    • Created an NBA similarity model for draft players for fan enhanced experience.
    Technologies: Python
  • Data Scientist

    2016 - 2017
    Alem Research
    • Scraped 10 million company front pages from a social network with Java.
    • Created a sentiment analysis neural network model using TensorFlow to label various English texts (including articles, comments, and more) as positive, negative, or neutral.
    Technologies: Java, Python

Experience

  • Neural Network Distilling Knowledge
    https://github.com/usholanb/Experiments-with-Distilling-Knowledge.git

    One of the hottest topics in the field of neural networks is knowledge distillation. Data scientists are curious about how compacted a neural net can become while still performing at a similar quality level.

    The approach is to use the layer before the last (output layer) and use it as an output layer for a smaller neural net (with less hidden layers).

    In this project, I used ten classes of ImageNet (around 1,000 pictures each) and trained two such neural nets. The results were the large model was 68% top 1. The smaller model (trained itself) was 56% top 1, and the distilled model was 56.5% top 1.

  • NFL Drive Outcome Prediction

    I implemented a neural network model for NFL drive outcome predictions. The framework is Pytorch and the predictions are used by betting companies for coefficients.

Skills

  • Languages

    Python, Java, SQL, C++, C, Scala, Python 3, Solidity
  • Libraries/APIs

    OpenCV, PyTorch, Scikit-learn, XGBoost, Lasagne, TensorFlow, Rasa NLU
  • Tools

    Git, Jira, Slack, SourceTree, Robomongo, PyCharm, Sublime Text 3, Microsoft Excel, MATLAB, GitLab, Sublime Text, You Only Look Once (YOLO)
  • Paradigms

    Object-oriented Programming (OOP), Agile Software Development
  • Platforms

    Amazon EC2 (Amazon Elastic Compute Cloud), Ubuntu, MacOS, Amazon Web Services (AWS)
  • Storage

    Amazon S3 (AWS S3), MongoDB, PostgreSQL, Elasticsearch
  • Other

    Artificial Intelligence (AI), Convolutional Neural Networks, Image Processing, Machine Learning, Video Processing, Neural Networks, Statistical Modeling, Deep Learning, Random Forests, Linear Regression, Logistic Regression, Data Versioning, Tf-idf, K-means Clustering, K-nearest Neighbors, Computer Vision, Natural Language Processing (NLP), AWS, Game Theory, Object Tracking, Chatbots, Moralis

Education

  • Bachelor of Science Degree in Computer Engineering
    2012 - 2016
    University of California, San Diego - San Diego, CA, USA

Certifications

  • Machine Learning
    SEPTEMBER 2017 - PRESENT
    Stanford University via Coursera

To view more profiles

Join Toptal
Share it with others