Biologically inspired heterogeneous learning for accurate, efficient and low-latency neural network.

The pursuit of artificial neural networks that mirror the accuracy, efficiency and low latency of biological neural networks remains a cornerstone of artificial intelligence (AI) research. Here, we incorporated recent neuroscientific findings of self-inhibiting autapse and neuron heterogeneity for innovating a spiking neural network (SNN) with enhanced learning and memorizing capacities. A bi-level programming paradigm was formulated to respectively learn neuron-level biophysical variables and network-level synapse weights for nested heterogeneous learning.

Residual DNN: training diffractive deep neural networks via learnable light shortcuts.

The diffractive deep neural network () has demonstrated its importance in performing various all-optical machine learning tasks, e.g., classification, segmentation, etc.