Laurens R. Leerink

Learn More
Product units provide a method of automatically learning the higher-order input combinations required for eecient learning in neural networks. However, we show that problems are encountered when using backpropagation to train networks containing these units. This paper examines these problems, and proposes some atypical heuristics to improve learning. Using(More)
This paper applies recent results from theoretical biology on the topic of ant trail formation and foraging methods to the problem of exploration in a discrete environment with delayed reinforcement. Three mechanisms that have been identiied in ant trail formation were implemented as an exploration strategy in the adaptive heuristic critic framework, and(More)
| We investigate the learning of de-terministic nite-state automata (DFA's) with recurrent networks with a single input neu-ron, where each input symbol is represented as a temporal pattern and strings as sequences of temporal patterns. We empirically demonstrate that obvious temporal encodings can make learning very diicult or even impossible. Based on(More)
We present an algorithm for the training of feedforward and recurrent neural networks. It detects internal representation conflicts and uses these conflicts in a constructive manner to add new neu-rons to the network. The advantages are twofold: (1) starting with a small network neurons are only allocated when required; (2) by detecting and resolving(More)
  • 1