Artificial Neural Networks and Machine Learning – ICANN 2025: 34th International Conference on Artificial Neural Networks, Kaunas, Lithuania, September 9–12, 2025, Proceedings, Part I(16068 Lecture Notes in Computer Science)

The four-volume set LNCS 16068-16071 constitutes the proceedings of the 34th International Conference on Artificial Neural Networks and Machine Learning, ICANN 2025, held in Kaunas, Lithuania, September 9–12, 2025. The 170 full papers and 8 abstracts included in these conference proceedings were carefully reviewed and selected from 375 submissions. The conference strongly values the synergy between theoretical progress and impactful real-world applications, and actively encourages contributions that demonstrate how artificial neural networks are being used to address pressing societal and technological challenges.

Table of Contents:
.- MRT-NAS: Boosting Training-free NAS via Manifold Regularization. .- MSfusion: A Dynamic Model Splitting Approach for Resource Constrained Machines to Collaboratively Train Larger Models. .- DeepCTL: Neural Branching-Time CTL Satisfiability Checking via Recursive Decision Trees. .- MFMamba: A Hierarchical Weakly Causal Mamba with Multi-Scale Feature Fusion for Vision Tasks. .- Characterizing trainability, expressivity and generalization of neural architecture with metrics from neural tangent kernel. .- Unrolled Neural Adaptive Alternating Gradient Descent for NMF. .- FedTP: Traceable Passport-based Ownership Verification for Federated Deep Neural Network Models. .- Learning to Optimize Entropy in the Soft Actor-Critic. .- Parallelizing Sharpness-Aware Minimization: A Semi-Asynchronous Small-Batch Approach. .- Small transformer architectures for task switching. .- Stochastic Covariance Regularization for Imbalanced Datasets. .- Efficient Learning in Spiking Neural Networks - Introducing Feedback Alignment to the Reinforced Liquid State Machine. .- Object-Centric Dreamer. .- How Inductive Biases Affect OOD Generalization: An Investigation in Formal Language Recognition with Autoregressive Models. .- Brain Generative Replay for Continual Learning. .- Dynamic Ensembles Towards Out-Of-Distribution Generalization of Affect Models. .- D2R: Dual Regularization Loss with Collaborative Adversarial Generation for Model Robustness. .- The Power of Max Pooling Layer. .- Firing rates and representational error in efficient spiking networks are bounded by design. .- CIBR: Cross-modal Information Bottleneck Regularization for Robust CLIP Generalization. .- Cascade Pre-Attention: Regulating Neuronal Activation Distributions in MetaFormer-Based Spiking Neural Networks. .- MTL-SIMNAS: Task Similarity-Driven Neural Architecture Search for Enhanced Multi-Task Learning. .- Towards Better Graph Anomaly Detection: A Performance-Aware Neural Architecture Search Approach. .- Improving Stability of Parameter Sharing in Cooperative Multi-Agent Reinforcement Learning. .- The Explainability-Performance Coefficient: A New Metric for Model Transparency. .- GLFMamba-U: Global-Local Fused Mamba-Unet. .- Continuous Fair SMOTE - Fairness-Aware Stream Learning from Imbalanced Data. .- Evaluating the Impact of Data Curation on Off-Policy Reinforcement Learning. .- Enhancing Graph Neural Networks with Mixup-Based Knowledge Distillation. .- A Framework for Uncertainty Quantification Based on Nearest Neighbors Across Layers. .- FedP2PAvg: A Peer-to-Peer Collaborative Framework for Federated Learning in Non-IID Scenarios. .- Correcting the Modified Stochastic Synaptic Model of Synaptic Dynamics - Refinement of Vesicle and Neurotransmitters Functions. .- Improving monotonic optimization in heterogeneous multi-agent reinforcement learning with optimal marginal deterministic policy gradient. .- Efficient ReliefF: A low-power optimization of ReliefF for resource-constrained devices. .- Enhancing Adversarial Robustness through Multi-Objective Representation Learning. .- Trustworthy Learning with Noisy Labels. .- Effect of Neuromodulation on the Brain Dynamical Repertoire. .- Classification of large data sets by neural networks: A probabilistic viewpoint. .- Identification and Realization of a Class of Discrete Event Systems by Neural Networks -Timed Petri Nets. .- Dopamine-modulated Learning and Decision-making with Neuromorphic Computing. .- A Unified Platform to Evaluate STDP Learning Rule and Synapse Model using Pattern Recognition in a Spiking Neural Network. .- XOOD: A Self-Supervised Algorithm for Detecting Out-of-Distribution Data for Image Classification. .- Perpetual Generation: Online Learning of Linear State-Space Models from a Single Stream. .- Accelerating Spatiotemporal Learning with minConvRNNs. .- Full Integer Arithmetic Online Training for Spiking Neural Networks. .- Regularised Loss Function for Goal Recognition as a Deep Learning Task. .- Improving Consistency Distillation with Rectified Trajectories. .- Merging versus Separating Replay Samples in Continual Learning. .- Signal-to-noise difference as a correlate of class learning in neural networks. .- Catastrophic Forgetting Mitigation via Discrepancy-Weighted Experience Replay. .- Supervised feature selection with class self-representation. .- Complexity and Criticality in Neuro-Inspired Reservoirs. .- A Fokker-Planck Perspective on the Flow of Information in Continuous Memory Neural Networks.