deep neural network

Entropy-based Activation Function Optimization: A Method on Searching Better Activation Functions ICLR 2025 Failure Cases Are Better Learned But Boundary Says Sorry: Facilitating Smooth Perception Change for Accuracy-Robustness Trade-Off in Adversarial Training ICCV 2025 FastCAV: Efficient Computation of Concept Activation Vectors for Explaining Deep Neural Networks ICML 2025 Feature Clipping for Uncertainty Calibration AAAI 2025 Four Axiomatic Characterizations of the Integrated Gradients Attribution Method JMLR 2025 Genomics Data Lossless Compression with (S, K)-Mer Encoding and Deep Neural Networks AAAI 2025 GPU-Accelerated Parallel Bilevel Optimization for Roubst 6G ISAC AAAI 2025 Has the Deep Neural Network learned the Stochastic Process? An Evaluation Viewpoint ICLR 2025 IITR-CIOL@NLU of Devanagari Script Languages 2025: Multilingual Hate Speech Detection and Target Identification in Devanagari-Scripted Languages COLING 2025 Improving Transferable Targeted Attacks with Feature Tuning Mixup CVPR 2025 Increasing Batch Size Improves Convergence of Stochastic Gradient Descent with Momentum ACML 2025 Information-theoretic reduction of deep neural networks to linear models in the overparametrized proportional regime COLT 2025 Joint Asymmetric Loss for Learning with Noisy Labels ICCV 2025 LaCoOT: Layer Collapse through Optimal Transport ICCV 2025 Learning Deep Illumination-Robust Features from Multispectral Filter Array Images WACV 2025 Leveraging Spatial Invariance to Boost Adversarial Transferability ICCV 2025 Local Linear Recovery Guarantee of Deep Neural Networks at Overparameterization JMLR 2025 Lyapunov Perception Contracts for Operating Design Domains L4DC 2025 Mapping Functional Language Areas with non-Functional Brain MRI MIDL 2025 Minimax Optimal Deep Neural Network Classifiers Under Smooth Decision Boundary JMLR 2025 Misclassification-driven Fingerprinting for DNNs Using Frequency-aware GANs IJCAI 2025 Monitoring Primitive Interactions During the Training of DNNs AAAI 2025 MOS-Attack: A Scalable Multi-objective Adversarial Attack Framework CVPR 2025 Multi-Channel Acoustic Echo Cancellation Based on Direction-of-Arrival Estimation Interspeech 2025 Multi-view Privileged Information-based Representation Learning for Liver Cancer Diagnosis ACML 2025