universal approximation property

6 papers

• A unified framework for establishing the universal approximation of transformer-type architectures
• Minimum Width for Deep, Narrow MLP: A Diffeomorphism Approach
• Optimal Minimum Width for the Universal Approximation of Continuously Differentiable Functions by Deep Narrow MLPs
• Shape-Informed Clustering of Multi-Dimensional Functional Data via Deep Functional Autoencoders
• Universally Invariant Learning in Equivariant GNNs
• Vocabulary In-Context Learning in Transformers: Benefits of Positional Encoding