Self-Supervised Interpretable End-to-End Learning via Latent Functional Modularity
We introduce MoNet, a novel functionally modular network for self-supervised and interpretable end-to-end learning. By leveraging its functional modularity with a latent-guided contrastive loss function, MoNet efficiently learns task-specific decision-making processes in latent space without requiring task-level supervision. Moreover, our method incorporates an online, post-hoc explainability approach that enhances the interpretability of end-to-end inferences without compromising sensorimotor control performance. In real-world indoor environments, MoNet demonstrates effective visual autonomous navigation, outperforming baseline models by 7% to 28% in task specificity analysis. We further explore the interpretability of our network through post-hoc analysis of perceptual saliency maps and latent decision vectors. This provides valuable insights into the incorporation of explainable artificial intelligence into robotic learning, encompassing both perceptual and behavioral perspectives. Supplementary materials are available at https://sites.google.com/view/monet-lgc.
Code (0)
등록된 구현이 없습니다.
Tasks
Autonomous NavigationDecision MakingExplainable artificial intelligenceSpecificityMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Leveraging Brain Modularity Prior for Interpretable Representation Learning of fMRI
Resting-state functional magnetic resonance imaging (rs-fMRI) can reflect spontaneous neural activities in brain and is widely used for brain disorder analysis.Previous studies propose to extract fMRI representations thr…
graph constructionGraph LearningGraph Neural NetworkRepresentation LearningInduced Modularity and Community Detection for Functionally Interpretable Reinforcement Learning
Interpretability in reinforcement learning is crucial for ensuring AI systems align with human values and fulfill the diverse related requirements including safety, robustness and fairness. Building on recent approaches …
Community DetectionFairnessreinforcement-learningReinforcement LearningFluctuations between high- and low-modularity topology in time-resolved functional connectivity
Modularity is an important topological attribute for functional brain networks. Recent studies have reported that modularity of functional networks varies not only across individuals being related to demographics and cog…
AttributeFunctional ConnectivityGenerative Modeling of Hidden Functional Brain Networks
Functional connectivity refers to the temporal statistical relationship between spatially distinct brain regions and is usually inferred from the time series coherence/correlation in brain activity between regions of int…
Functional ConnectivityTime SeriesTime Series AnalysisUnsupervised Discovery of Interpretable Directions in the GAN Latent Space
The latent spaces of GAN models often have semantically meaningful directions. Moving in these directions corresponds to human-interpretable image transformations, such as zooming or recoloring, enabling a more controlla…
Saliency Detection