17 citations · 21 across the 4 of their papers we have counts for
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2021★ 1 cited
Fast Concept Mapping: The Emergence of Human Abilities in Artificial Neural Networks when Learning Embodied and Self-Supervised
Viviane Clay, Peter König, Gordon Pipa +1
Most artificial neural networks used for object detection and recognition are trained in a fully supervised setup. This is not only very resource consuming as it requires large dat…
cs.LG2018
Adaptive Blending Units: Trainable Activation Functions for Deep Neural Networks
Leon René Sütfeld, Flemming Brieger, Holger Finger +2
The most widely used activation functions in current deep feed-forward neural networks are rectified linear units (ReLU), and many alternatives have been successfully applied, as w…