most citedOn the existence of infinitely many realization functions of non-global local minima in the training of artificial neural networks with ReLU activation

1 citations · 1 across the 1 of their papers we have counts for

collaborators

1 paper

math.OC2022★ 1 cited

On the existence of infinitely many realization functions of non-global local minima in the training of artificial neural networks with ReLU activation

Shokhrukh Ibragimov, Arnulf Jentzen, Timo Kröger +1

Gradient descent (GD) type optimization schemes are the standard instruments to train fully connected feedforward artificial neural networks (ANNs) with rectified linear unit (ReLU…