Marco Paul E. Apolinario

Marco Paul E. Apolinario works on brain-inspired computing, developing learning algorithms and hardware designs for spiking neural networks (models that mimic how neurons communicate using discrete pulses rather than continuous signals). Recent work focuses on efficient, biologically-inspired training methods (local learning rules that avoid some computational overhead of standard deep learning), continual learning (enabling models to learn new tasks without forgetting old ones), and combining event-based and image-based sensor data for tasks like segmentation and gesture recognition. Earlier work applied deep learning to practical problems such as timber species identification and river level estimation using computer vision.

Publication output has grown over the past decade, rising from occasional single papers per year (2018-2021) to a more steady output of 2-4 papers annually from 2022 through 2025.

Generated by claude-sonnet-5 from public bibliographic data · Jul 20, 2026