Skip to content
View OliverGrainge's full-sized avatar
7 followers · 0 following

Achievements

Achievement: Pull Shark

Achievements

Achievement: Pull Shark

Block or report OliverGrainge

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 supported. This note will be visible to only you.
Report abuse

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

Report abuse
OliverGrainge/README.md

Hi there 👋

I'm Oliver Grainge, a researcher and engineer passionate about machine intelligence, computer vision and NLP.

🔭 I’m currently working on:

  • Developing efficient low-bit quantized neural networks for resource-constrained devices.
  • Binary and Ternary Quantization techniques for Transformer Networks
  • Pruning methods for neural network compression

🌱 I’m currently learning:

  • Advanced neural network compression techniques.
  • Exploring large-scale language models for generative AI.

👯 I’m looking to collaborate on:

  • Open-source AI projects related to computer vision and neural network optimization.
  • Research collaborations focused on AI applications in embedded systems.

📫 How to reach me:

Pinned Loading

  1. BitOps BitOps Public

    High-performance ternary matrix multiplication for quantized neural networks. 16× memory reduction with CPU (NEON/AVX2) and CUDA backends.

    C 2

  2. BitCore BitCore Public

    Quantization-aware ternary linear layers for PyTorch. Drop-in nn.Linear replacement with training and optimized deployment modes.

    Python

  3. TeTRA-VPR TeTRA-VPR Public

    Research code for a fully quantized image retrieval pipeline using ternary networks and binary descriptors for efficient visual place recognition.

    Python 6 1

  4. VSLAM VSLAM Public

    Stereo Visual SLAM in pure Python. Feature detection, tracking, motion estimation, and optimization using NumPy, OpenCV, and SciPy.

    Python