Tag
This paper proposes Dualformer, a dual-channel neural network architecture based on transformers, designed for efficient feature extraction from complex-valued signals in blind communication analysis tasks such as automatic modulation recognition, signal scheme recognition, and signal structure parsing. Extensive experiments show consistent performance improvements over existing methods.
This paper presents a retrospective on the design evolution of SWave, a complex-valued recurrent language model, detailing which architectural components were retained, reframed, superseded, or proved non-load-bearing, along with formal characterizations of failure modes like cos-domination collapse.
This paper proposes a novel complex-valued gated recurrent unit (GRU) architecture with multiplicative product units (AM-PU-GRU) for predicting nuclear masses, achieving state-of-the-art interpolation and extrapolation accuracy on the Atomic Mass Evaluation datasets.