Brain-Inspired AI

Exploring how psychological and neuroscientific knowledge can advance machine models presents a promising research direction. Our group is interested in investigating machine models that not only mirror biological systems but also provide tangible advantages for applications in the real world.

Interestingly, it is crucial to recognize that many machine models have been influenced by discoveries in neuroscience. For example, the foundational principles of popular machine models such as convolutional neural networks, recurrent neural networks, and reinforcement learning can be traced back to theories and findings within psychology and neuroscience. Given the brain’s evolutionary refinement over millions of years for efficient adaptation to the visual world, it can serve as a valuable reference for understanding and modeling intelligence.

The rapid advancements in deep learning techniques has sparked debate over the significance of the brain in understanding and modeling intelligence. Despite some machine models achieving remarkable performance from purely engineering-driven approaches, we believe that they still lack essential components of human cognition, which could be pivotal for enhancing their efficacy and reliability. Our group has recently proposed that mimicking the developmental trajectory of infant vision may provide beneficial strategies for integrative face processing (Jang and Tong, Journal of Vision, 2021).

We aim to pursue this line of research, currently focusing on the following topics:

  • Recurrent processing
  • Predictive coding
  • Developmetnal learning

Image from Jang and Tong, Journal of Vision, 2021

Hojin Jang
Hojin Jang
Assistant Professor