Name
Abstract | ||
|---|---|---|
Existing approaches to combine both additive and multiplicative neural units either use a fixed assignment of operations or require discrete optimization to determine what function a neuron should perform. However, this leads to an extensive increase in the computational complexity of the training procedure. We present a novel, parameterizable transfer function based on the mathematical concept of non-integer functional iteration that allows the operation each neuron performs to be smoothly and, most importantly, differentiablely adjusted between addition and multiplication. This allows the decision between addition and multiplication to be integrated into the standard backpropagation training procedure. |
Year | Venue | Field |
|---|---|---|
2016 | arXiv: Learning | Mathematical optimization,Multiplicative function,Discrete optimization,Differentiable function,Transfer function,Multiplication,Artificial intelligence,Backpropagation,Machine learning,Mathematics,Computational complexity theory |
DocType | Volume | Citations |
Journal | abs/1604.03736 | 0 |
PageRank | References | Authors |
0.34 | 2 | 3 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Wiebke Köpp | 1 | 0 | 0.34 |
| Patrick van der Smagt | 2 | 188 | 24.23 |
| Sebastian Urban | 3 | 22 | 5.38 |