Start Date
5-12-2025 12:00 PM
End Date
5-12-2025 1:00 PM
Description
Backpropagation (BP) relies on biologically implausible mechanisms like global error transport. This project investigates two alternatives: Error-Driven Local Representation Alignment (LRA), which utilizes local error loops, and Predictive Forward-Forward (PFF), which employs forward-forward algorithm and "goodness" optimization to eliminate backward passes. We quantify the trade-off between biological plausibility and efficiency by measuring the convergence lag inherent to localized updates. Theoretically, we analyze how PFF and LRA resolve the weight transport problem and enable local credit assignment, positioning these frameworks as viable candidates for energy-efficient "mortal computation" on neuromorphic hardware.
Biologically Motivated Algorithms and Backpropagation
Backpropagation (BP) relies on biologically implausible mechanisms like global error transport. This project investigates two alternatives: Error-Driven Local Representation Alignment (LRA), which utilizes local error loops, and Predictive Forward-Forward (PFF), which employs forward-forward algorithm and "goodness" optimization to eliminate backward passes. We quantify the trade-off between biological plausibility and efficiency by measuring the convergence lag inherent to localized updates. Theoretically, we analyze how PFF and LRA resolve the weight transport problem and enable local credit assignment, positioning these frameworks as viable candidates for energy-efficient "mortal computation" on neuromorphic hardware.