fully-connected network

Knowledge Graphs Can be Learned with Just Intersection Features ICML 2024 Transformers Provably Learn Sparse Token Selection While Fully-Connected Nets Cannot ICML 2024 Predicting Temporal Sets with Simplified Fully Connected Networks AAAI 2023 Training Fully Connected Neural Networks is $\exists\mathbb{R}$-Complete NeurIPS 2023 Reverse Engineering the Neural Tangent Kernel ICML 2022 A Probabilistic Approach to Neural Network Pruning ICML 2021 Computational Separation Between Convolutional and Fully-Connected Networks ICLR 2021 Why Are Convolutional Nets More Sample-Efficient than Fully-Connected Nets? ICLR 2021 Disentangling Trainability and Generalization in Deep Neural Networks ICML 2020 Towards Learning Convolutions from Scratch NeurIPS 2020 Finding the Needle in the Haystack with Convolutions: on the benefits of architectural bias NeurIPS 2019 Semantic Segmentation With Object Clique Potential ICCV 2015