theNatives
  • Studio
  • Research

Research

A record of our technical methodology. Algorithms, mathematical formulations, machine learning approaches, and reviews of industry literature.

  • Item2Vec for Sparse Purchase Histories: Embedding Products in Implicit Feedback Regimes Jun 2025 How we adapted Word2Vec's skip-gram architecture to learn product embeddings from sparse, implicit purchase signals — without collaborative filtering at scale. machine-learningembeddingsrecommender-systemsnlp
  • ResNet-18 for Image Classification: Residual Learning on MNIST and CIFAR-10 May 2025 How we implemented a ResNet-18 classification system with dual CLI/GUI interfaces, and what the residual connection formulation buys you over plain convolutional stacks. computer-visioncnndeep-learningclassificationpytorch
  • Semantic Segmentation of Land Cover from Multispectral Imagery: A CNN Approach Apr 2025 Our methodology for training a convolutional segmentation model to classify land cover types from optical multiband satellite imagery, and how we packaged it as a QGIS plugin. computer-visioncnnremote-sensinggeospatial
  • Liver Segmentation from CT Scans: U-Net with Combined Dice–BCE Loss and HU Windowing Mar 2025 Our modular PyTorch pipeline for segmenting liver regions from CT imagery — covering the U-Net architecture, Hounsfield unit windowing, combined loss formulation, and the full suite of segmentation metrics. computer-visionsegmentationmedical-imagingunetpytorch

theNatives — Nairobi, Kenya

Est. 2026