Taewook Hwang  Hyein Seo  Sangkeun Jung

10.5626/JOK.2026.53.3.190

Deep Learning Algorithms forward-forward algorithm Backpropagation Algorithm Few-Shot Learning vector memory

The Forward-Forward algorithm introduces a new approach to replace backpropagation, which learns independently for each layer, akin to the functioning of the human brain. However, this independent learning raises concerns about the transmission of information between layers. In this study, we propose a method that assigns a dedicated memory space to each layer, emulating human memory, to enhance information transfer between layers. We store the average output values for each label in memory and employ an angular margin loss function to measure the difference between these stored values and the current layer's output, ensuring that each label is represented at distinct angles. Additionally, we compare the memory values from the previous layer with the current layer's output using the angular margin loss function to facilitate alignment with the previous layer's angle. Experimental results indicate that, despite initial limitations with very limited data, our proposed method achieved 90.71% accuracy on the MNIST dataset with a sufficient data volume (100-shot), outperforming the existing Forward-Forward algorithm, which achieved 89.63% accuracy.