Towards binary encoding in Bidirectional Associative Memories

Bidirectional Associative Memories (BAMs) are Artificial Neural Networks frequently utilized in cognitive modeling. While bipolar encoding is commonly used BAMs for optimal performance, binary presents interesting properties. As such, this study introduces a novel transmission function and compares its performance to the conventional function. To evaluate, an auto-association learning task noisy recall were implemented. Results revealed that despite longer times, preserves or enhances properties observed encoding. Findings promising from perspective, as they open possibility of building intricate models human cognition.