Computing with Canonical Microcircuits
This work addresses efficiency and interpretability issues in AI for researchers and practitioners, though it is incremental as it builds on existing neuromorphic and brain-inspired approaches.
The authors tackled the problem of inefficient and non-interpretable AI by proposing a neuromorphic architecture based on canonical microcircuits, achieving 97.8% accuracy on MNIST with fewer parameters than conventional models and competitive results on complex image benchmarks.
The human brain represents the only known example of general intelligence that naturally aligns with human values. On a mere 20-watt power budget, the brain achieves robust learning and adaptive decision-making in ways that continue to elude advanced AI systems. Inspired by the brain, we present a computational architecture based on canonical microcircuits (CMCs) - stereotyped patterns of neurons found ubiquitously throughout the cortex. We implement these circuits as neural ODEs comprising spiny stellate, inhibitory, and pyramidal neurons, forming an 8-dimensional dynamical system with biologically plausible recurrent connections. Our experiments show that even a single CMC node achieves 97.8 percent accuracy on MNIST, while hierarchical configurations - with learnable inter-regional connectivity and recurrent connections - yield improved performance on more complex image benchmarks. Notably, our approach achieves competitive results using substantially fewer parameters than conventional deep learning models. Phase space analysis revealed distinct dynamical trajectories for different input classes, highlighting interpretable, emergent behaviors observed in biological systems. These findings suggest that neuromorphic computing approaches can improve both efficiency and interpretability in artificial neural networks, offering new directions for parameter-efficient architectures grounded in the computational principles of the human brain.