AINeutralarXiv – CS AI · 8h ago6/10
🧠
An Empirical Audit of Input Encoders for Multi-Channel Signal Transformers
Researchers empirically compared eight input encoder architectures for Transformer models processing multi-channel signal data, finding that the standard per-channel linear projection matches all alternatives in performance while being simplest to implement. Two encoders underperformed significantly: shared-scalar baselines and channel-independent architectures, with practical differences between top performers remaining statistically small but modest.