deep-neural-networks

Documents about deep-neural-networks

• Topology-Preserving Neural Operator Learning via Hodge Decomposition#180639arXiv CS
• Benchmarking Optimizers for MLPs in Tabular Deep Learning#18995arXiv CS
• FedSPDnet: Geometry-Aware Federated Deep Learning with SPDnet#134557arXiv CS
• A Functorial Formulation of Neighborhood Aggregating Deep Learning#138917arXiv CS
• Natural Riemannian gradient for learning functional tensor networks#5980arXiv CS
• A Complete Symmetry Classification of Shallow ReLU Networks#14013arXiv CS
• A unified deep learning framework integrating OpenStreetMap for multi-domain urban planning tasks#5854Europe PMC
• Continuous Adversarial Flow Models#10358arXiv CS
• Multistage Conditional Compositional Optimization#14009arXiv CS
• Bounded Ratio Reinforcement Learning#120494arXiv CS
• Near-Future Policy Optimization#124051arXiv CS
• Quotient-Space Diffusion Models#126508arXiv CS
• Stochastic simultaneous optimistic optimization#138934arXiv CS
• Recursive Multi-Agent Systems#141465arXiv CS
• Deflation-Free Optimal Scoring#141484arXiv CS
• ELF: Embedded Language Flows#175237arXiv CS
• Mistake-Bounded Language Generation#175268arXiv CS
• High-arity Sample Compression#178868arXiv CS
• Brain tumor segmentation with Deep Neural Networks#6629OpenAlex
• Variational Quantum Physics-Informed Neural Networks for Hydrological PDE-Constrained Learning with Inherent Uncertainty Quantification#5966arXiv CS
• Scalable Neural Decoders for Practical Fault-Tolerant Quantum Computation#2602arXiv CS
• Structure as Computation: Developmental Generation of Minimal Neural Circuits#19016arXiv CS
• SafeAdapt: Provably Safe Policy Updates in Deep Reinforcement Learning#5952arXiv CS
• AdaCubic: An Adaptive Cubic Regularization Optimizer for Deep Learning#5956arXiv CS
• There Will Be a Scientific Theory of Deep Learning#126520arXiv CS
• Locking Pretrained Weights via Deep Low-Rank Residual Distillation#175278arXiv CS
• Trajectory-Agnostic Asteroid Detection in TESS with Deep Learning#178883arXiv CS
• Toward World Models for Epidemiology#5948arXiv CS
• Token Encoding for Semantic Recovery#13085arXiv CS
• Generative Anonymization in Event Streams#13093arXiv CS
• Learning to Concatenate Quantum Codes#19031arXiv CS
• Neural Networks and Deep Learning#112363PhilArchive
• Sessa: Selective State Space Attention#120493arXiv CS
• The Sample Complexity of Multicalibration#126496arXiv CS
• Mixed Membership sub-Gaussian Models#134541arXiv CS
• Prior-Agnostic Robust Forecast Aggregation#138936arXiv CS
• Kwai Summary Attention Technical Report#138943arXiv CS
• Certified geometric robustness -- Super-DeepG#138948arXiv CS
• Dictionary learning for Kernel EDMD#141489arXiv CS
• Computing Equilibrium beyond Unilateral Deviation#146906arXiv CS
• Randomized Subspace Nesterov Accelerated Gradient#151726arXiv CS
• Spiking Sequence Machines and Transformers#151737arXiv CS
• Budget Constraints as Riemannian Manifolds#151740arXiv CS
• Distributionally-Robust Learning to Optimize#168327arXiv CS
• Manifold Sampling via Entropy Maximization#178899arXiv CS
• Variational Inference for Lévy Process-Driven SDEs via Neural Tilting#175238arXiv CS
• Neural-Schwarz Tiling for Geometry-Universal PDE Solving at Scale#178895arXiv CS
• Monte Carlo Stochastic Depth for Uncertainty Estimation in Deep Learning#13101arXiv CS
• MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications#6519OpenAlex
• Randomly Initialized Networks Can Learn from Peer-to-Peer Consensus#120532arXiv CS