Showing cs.LGShow all
3 papers · 1 filter
cs.LG2025
UNO: Unlearning via Orthogonalization in Generative models
Pinak Mandal, Georg A. Gottwald
As generative models become increasingly powerful and pervasive, the ability to unlearn specific data due to privacy concerns, legal requirements, or harmful content has become inc…
cs.LG2025
Learning dynamical systems with hit-and-run random feature maps
Pinak Mandal, Georg A. Gottwald
We show how random feature maps can be used to forecast dynamical systems with excellent forecasting skill. We consider the tanh activation function and judiciously choose the inte…
cs.LG2024
On the choice of the non-trainable internal weights in random feature maps
Pinak Mandal, Georg A. Gottwald, Nicholas Cranch
The computationally cheap machine learning architecture of random feature maps can be viewed as a single-layer feedforward network in which the weights of the hidden layer are rand…