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

• URL: http://arxiv.org/abs/2505.15570v1
• Date: Wed, 21 May 2025 14:23:38 GMT
• Title: Refining Neural Activation Patterns for Layer-Level Concept Discovery in Neural Network-Based Receivers
• Authors: Marko Tuononen, Duy Vu, Dani Korpi, Vesa Starck, Ville Hautamäki,
• Abstract summary: Concept discovery in neural networks often targets individual neurons or human-interpretable features, overlooking distributed layer-wide patterns.<n>We study the Neural Activation Pattern (NAP) methodology, which clusters full-layer activation distributions to identify such layer-level concepts.<n>In the radio receiver model, distinct concepts did not emerge; instead, a continuous activation manifold shaped by Signal-to-Noise Ratio (SNR) was observed.
• Score: 5.668124846154998
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Concept-Guided Interpretability via Neural Chunking [54.73787666584143]
  We show that neural networks exhibit patterns in their raw population activity that mirror regularities in the training data.<n>We propose three methods to extract these emerging entities, complementing each other based on label availability and dimensionality.<n>Our work points to a new direction for interpretability, one that harnesses both cognitive principles and the structure of naturalistic data.
  arXiv  Detail & Related papers  (2025-05-16T13:49:43Z)
• Learning local discrete features in explainable-by-design convolutional neural networks [0.0]
  We introduce an explainable-by-design convolutional neural network (CNN) based on the lateral inhibition mechanism. The model consists of the predictor, that is a high-accuracy CNN with residual or dense skip connections. By collecting observations and directly calculating probabilities, we can explain causal relationships between motifs of adjacent levels.
  arXiv  Detail & Related papers  (2024-10-31T18:39:41Z)
• Interpreting Deep Neural Network-Based Receiver Under Varying Signal-To-Noise Ratios [6.643082745560234]
  We propose a novel method for interpreting neural networks, focusing on convolutional neural network-based receiver model.<n>The method identifies which unit or units of the model contain most (or least) information about the channel parameter(s) of the interest.<n> Experiments on link-level simulations demonstrate the method's effectiveness in identifying units that contribute most (and least) to signal-to-noise ratio processing.
  arXiv  Detail & Related papers  (2024-09-25T09:26:19Z)
• DCNN: Dual Cross-current Neural Networks Realized Using An Interactive Deep Learning Discriminator for Fine-grained Objects [48.65846477275723]
  This study proposes novel dual-current neural networks (DCNN) to improve the accuracy of fine-grained image classification. The main novel design features for constructing a weakly supervised learning backbone model DCNN include (a) extracting heterogeneous data, (b) keeping the feature map resolution unchanged, (c) expanding the receptive field, and (d) fusing global representations and local features.
  arXiv  Detail & Related papers  (2024-05-07T07:51:28Z)
• Manipulating Feature Visualizations with Gradient Slingshots [54.31109240020007]
  We introduce a novel method for manipulating Feature Visualization (FV) without significantly impacting the model's decision-making process. We evaluate the effectiveness of our method on several neural network models and demonstrate its capabilities to hide the functionality of arbitrarily chosen neurons.
  arXiv  Detail & Related papers  (2024-01-11T18:57:17Z)
• Analyzing Populations of Neural Networks via Dynamical Model Embedding [10.455447557943463]
  A core challenge in the interpretation of deep neural networks is identifying commonalities between the underlying algorithms implemented by distinct networks trained for the same task. Motivated by this problem, we introduce DYNAMO, an algorithm that constructs low-dimensional manifold where each point corresponds to a neural network model, and two points are nearby if the corresponding neural networks enact similar high-level computational processes. DYNAMO takes as input a collection of pre-trained neural networks and outputs a meta-model that emulates the dynamics of the hidden states as well as the outputs of any model in the collection.
  arXiv  Detail & Related papers  (2023-02-27T19:00:05Z)
• Gradient Descent in Neural Networks as Sequential Learning in RKBS [63.011641517977644]
  We construct an exact power-series representation of the neural network in a finite neighborhood of the initial weights. We prove that, regardless of width, the training sequence produced by gradient descent can be exactly replicated by regularized sequential learning.
  arXiv  Detail & Related papers  (2023-02-01T03:18:07Z)
• WLD-Reg: A Data-dependent Within-layer Diversity Regularizer [98.78384185493624]
  Neural networks are composed of multiple layers arranged in a hierarchical structure jointly trained with a gradient-based optimization. We propose to complement this traditional 'between-layer' feedback with additional 'within-layer' feedback to encourage the diversity of the activations within the same layer. We present an extensive empirical study confirming that the proposed approach enhances the performance of several state-of-the-art neural network models in multiple tasks.
  arXiv  Detail & Related papers  (2023-01-03T20:57:22Z)
• A Generic Shared Attention Mechanism for Various Backbone Neural Networks [53.36677373145012]
  Self-attention modules (SAMs) produce strongly correlated attention maps across different layers. Dense-and-Implicit Attention (DIA) shares SAMs across layers and employs a long short-term memory module. Our simple yet effective DIA can consistently enhance various network backbones.
  arXiv  Detail & Related papers  (2022-10-27T13:24:08Z)
• Spiking Generative Adversarial Networks With a Neural Network Discriminator: Local Training, Bayesian Models, and Continual Meta-Learning [31.78005607111787]
  Training neural networks to reproduce spiking patterns is a central problem in neuromorphic computing. This work proposes to train SNNs so as to match spiking signals rather than individual spiking signals.
  arXiv  Detail & Related papers  (2021-11-02T17:20:54Z)
• Learning distinct features helps, provably [98.78384185493624]
  We study the diversity of the features learned by a two-layer neural network trained with the least squares loss. We measure the diversity by the average $L$-distance between the hidden-layer features.
  arXiv  Detail & Related papers  (2021-06-10T19:14:45Z)
• Generate and Verify: Semantically Meaningful Formal Analysis of Neural Network Perception Systems [2.2559617939136505]
  Testing remains to evaluate accuracy of neural network perception systems. We employ neural network verification to prove that a model will always produce estimates within some error bound to the ground truth.
  arXiv  Detail & Related papers  (2020-12-16T23:09:53Z)
• Neural Networks with Recurrent Generative Feedback [61.90658210112138]
  We instantiate this design on convolutional neural networks (CNNs) In the experiments, CNN-F shows considerably improved adversarial robustness over conventional feedforward CNNs on standard benchmarks.
  arXiv  Detail & Related papers  (2020-07-17T19:32:48Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.