Skip to content
View chmcbs's full-sized avatar
  • United Kingdom

Block or report chmcbs

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
chmcbs/README.md

ML Engineer @ Unilever

Python PyTorch FastAPI Docker Databricks MLflow Hugging Face

Featured Work:

  1. HeadCount β€” DeepLabV3+ segmentation for wheat head counting (computer vision)
  2. Bolongo β€” NLP chatbot with intent classification and automated training data generation
  3. chinese-noun-embeddings β€” Transformer embedding analysis and clustering for semantic structure

Currently...

  • Improving large-scale demand forecasts across Europe for Unilever
  • Building an automated arXiv research assistant with hybrid search and feedback-driven ranking
  • Practising algorithms and data structures on NeetCode

Pinned Loading

  1. HeadCount HeadCount Public

    Semantic segmentation model for counting wheat heads in field images, designed for yield estimation, flowering time detection, and field maturity assessment.

    Jupyter Notebook

  2. Bolongo Bolongo Public

    Template-based NLP chatbot for Old School RuneScape that provides accurate answers to natural language questions about tree farming.

    Python

  3. chinese-noun-embeddings chinese-noun-embeddings Public

    Explores how transformer encoders represent Chinese nouns, showing morphology dominates over semantic categories.

    Jupyter Notebook

  4. arXivAssistant arXivAssistant Public

    Automated research assistant with hybrid search, feedback-driven ranking, and LLM explanations.

    Python