Fields- Workshop on Neural Networks and Deep Learning
-
Title: Black-Box Optimization with a Novel Nonlocal Gradient and Its Applications to Deep Learning
Speaker:
Link:
-
Title: The universal approximation theorem for complex-valued neural networks
Speaker:
Link:
-
Title:
Speaker:
Link:
-
Title: Fundamental limits of deep neural network learning
Speaker:
Link:
-
Title: Neural-network based learning of functions with singularities
Speaker:
Link:
-
Title: Neural Network Approximation III: The curse of dimensionality
Speaker:
Link:
-
Title: Neural Network Approximation II: The role of depth
Speaker:
Link:
-
Title: Neural Network Approximation I : Foundations and basic approximation theory of neural networks
Speaker:
Link:
-
Title: Local Signal Adaptivity: Feature learning in Neural networks beyond kernels
Speaker:
Link:
-
Title: Tight upper bounds for expressivity of one-dimensional deep ReLU networks
Speaker:
Link:
-
Title: Unifying variational formulation of supervised learning: From kernel methods to neural networks
Speaker:
Link:
-
Title: Approximate Orthogonality and non-harmonic Fourier Frames on the Ball
Speaker:
Link:
-
Title: Parseval Proximal Neural Networks
Speaker:
Link:
-
Title: Margins and Neural Collapse in Deep Learning
Speaker:
Link:
-
Title: Deterministic and Stochastic Modeling of Evolution Operators using Deep Networks
Speaker:
Link:
-
Title: Semantic Information Pursuit
Speaker:
Link:
-
Title: Semantic Information Pursuit
Speaker:
Link:
-
Title: Non-convex penalization for training sparse neural networks
Speaker:
Link:
-
Title: Deep neural Networks are effective at learning high-dimensional Banach-valued functions from limited data
Speaker:
Link:
-
Title: Graph signal sampling and interpolation based on clusters and averages
Speaker:
Link: