← All research

Research · since 2018

Two hemispheres

Why do brains have two hemispheres, and can the asymmetry improve deep learning, RL and robotics?

Working on it now

Kevin Ryan

PhD · UNSW · 2026 to present

Bi-hemispheric continual RL

About Kevin’s project →

How we got here

  1. 2018
    Request for Research published with WBAI: Left and Right Neural Networks, inspired by our bilateral brains Read the brief ↗
  2. 2021
    Amir Mayan, Masters · Monash bicameral networks on CIFAR-100About Amir’s project →
  3. 2021
    Chandramouli Rajagopalan, Intern bilateral deep learning for image recognitionAbout Chandramouli’s project →Deep learning in a bilateral brain with hemispheric specialization · ACAIN 2024Now: Masters at UCSD
  4. 2022
    Yanfeng, Masters · Monash extending bilateral deep learningAbout Yanfeng’s project →
  5. 2023
  6. 2023
  7. 2024
    Haowei Yue, Masters · Monash adding a corpus callosumAbout Haowei’s project →
  8. 2024
    Joel Reji, Masters · Monash hemisphere selection by confidenceAbout Joel’s project →
  9. 2024
    Ben Smith, Masters · Monash bilateral continual learningAbout Ben’s project →
  10. 2026
    Jingwen Li, Masters · Monash extending left/right motor controlAbout Jingwen’s project →

Project notes

Why do brains have 2 hemispheres? And can it improve Deep Learning and AI? (2021-2022)

Two network diagrams side by side: on the left, clustered, tightly interconnected nodes; on the right, sparse long lines crossing the whole panel, illustrating different connectivity patterns in the two hemispheres.

The brains of all bilaterally symmetric animals on Earth are Bicameral – they are divided into left and right hemispheres. It must be important for intelligence. In this project we mimic observed differences and show a benefit for AI. See the poster presented at NAISys2022. And the preprint.