Refining Neural Activation Patterns for Layer-Level Concept Discovery in Neural Network-Based Receivers

Concept discovery in neural networks often targets individual neurons or human-interpretable features, overlooking distributed layer-wide patterns. We study the Neural Activation Pattern (NAP) methodology, which clusters full-layer activation distributions to identify such layer-level concepts. Applied to visual object recognition and radio receiver models, we propose improved normalization, distribution estimation, distance metrics, and varied cluster selection. In the radio receiver model, distinct concepts did not emerge; instead, a continuous activation manifold shaped by Signal-to-Noise Ratio (SNR) was observed -- highlighting SNR as a key learned factor, consistent with classical receiver behavior and supporting physical plausibility. Our enhancements to NAP improved in-distribution vs. out-of-distribution separation, suggesting better generalization and indirectly validating clustering quality. These results underscore the importance of clustering design and activation manifolds in interpreting and troubleshooting neural network behavior.

DeepRx MIMO: Convolutional MIMO Detection with Learned Multiplicative Transformations

Recently, deep learning has been proposed as a potential technique for improving the physical layer performance of radio receivers. Despite the large amount of encouraging results, most works have not considered spatial multiplexing in the context of multiple-input and multiple-output (MIMO) receivers. In this paper, we present a deep learning-based MIMO receiver architecture that consists of a ResNet-based convolutional neural network, also known as DeepRx, combined with a so-called transformation layer, all trained together. We propose two novel alternatives for the transformation layer: a maximal ratio combining-based transformation, or a fully learned transformation. The former relies more on expert knowledge, while the latter utilizes learned multiplicative layers. Both proposed transformation layers are shown to clearly outperform the conventional baseline receiver, especially with sparse pilot configurations. To the best of our knowledge, these are some of the first results showing such high performance for a fully learned MIMO receiver.