ePC: Fast and Deep Predictive Coding in Digital Simulation
Researchers have developed a new method called error-based Predictive Coding (ePC) that significantly speeds up neural network training on digital hardware. Traditional Predictive Coding (PC) methods suffer from signal decay in simulations, hindering their effectiveness with deeper networks. ePC reformulates PC to eliminate this decay, allowing it to achieve performance comparable to backpropagation even on complex models, while running orders of magnitude faster. AI
IMPACT This new training method could enable the development of deeper and more complex neural networks on existing digital hardware.