Search Results for author:
Found 3 papers, 2 papers with code
Complexity of Deciding Injectivity and Surjectivity of ReLU Neural Networks
In addition, we also characterize surjectivity for two-layer ReLU networks with one-dimensional output.
Towards Lower Bounds on the Depth of ReLU Neural Networks
We contribute to a better understanding of the class of functions that can be represented by a neural network with ReLU activations and a given architecture.
Provably Good Solutions to the Knapsack Problem via Neural Networks of Bounded Size
The development of a satisfying and rigorous mathematical understanding of the performance of neural networks is a major challenge in artificial intelligence.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
