24 November 2025
Time series and sequential data are widespread in many real-world environments. However, implementing physical and adaptive dynamical systems remains a challenge. Direct Feedback Alignment (DFA) is a learning algorithm for neural networks that overcomes some of the limits of backpropagation and can be implemented in neuromorphic hardware (e.g., photonic accelerators). Until now, DFA has been investigated mainly for feedforward architectures.
In this work, EMERGE partners from the University of Pisa adapt DFA for both “vanilla” and gated recurrent networks. Unlike backpropagation, the update rule of their DFA can be applied in parallel across time steps, thus removing the sequential propagation of errors. The authors benchmark DFA on 4 datasets for sequence classification tasks. Although backpropagation still achieves a better predictive accuracy, their DFA shows promising results, especially for environments and physical systems where backpropagation is unavailable.
Read the paper in the link below.
More Information
