Folding networks, a generalization of recurrent neural networks to tree structured inputs, are investigated as a mechanism to learn regularities on classical symbolic data, for example. The architecture, the training mechanism, and several applications in different areas are explained. After wards a theoretical foundation, proving that the approach is appropriate as a learning mechanism in principle, is presented: Their universal approximation ability is investigated - including several new results for standard recurrent neural networks such as explicit bounds on the required number of...
Folding networks, a generalization of recurrent neural networks to tree structured inputs, are investigated as a mechanism to learn regularities on cl...
