The search for the optimal word sequence can be performed efficiently even in a speech recognizer with a very large vocabulary and complex models. This is achieved using pruning methods with empirically chosen parameters and the willingness to accept a certain amount of pruning errors. Quite unsatisfying though, it is state-of-the-art that such pruning errors are not directly detected but, inst...

Axon pruning and synapse elimination promote neural connectivity and synaptic plasticity. Stereotyped pruning of axons that originate in the hippocampal dentate gyrus (DG) and extend along the infrapyramidal tract (IPT) occurs during postnatal murine development by neurite retraction and resembles axon repulsion. The chemorepellent Sema3F is required for IPT axon pruning, dendritic spine remode...

Pre-Pruning and Post-Pruning are two standard methods of dealing with noise in concept learning. Pre-Pruning methods are very efficient, while Post-Pruning methods typically are more accurate, but much slower, because they have to generate an overly specific concept description first. We have experimented with a variety of pruning methods, including two new methods that try to combine and integ...

Developmental axon pruning is essential for normal brain wiring in vertebrates and invertebrates. How axon pruning occurs in vivo is not well understood. In a mosaic loss-of-function screen, we found that Bsk, the Drosophila JNK, is required for axon pruning of mushroom body γ neurons, but not their dendrites. By combining in vivo genetics, biochemistry, and high-resolution microscopy, we demon...

Recent DNN pruning algorithms have succeeded in reducing the number of parameters in fully connected layers, often with little or no drop in classification accuracy. However, most of the existing pruning schemes either have to be applied during training or require a costly retraining procedure after pruning to regain classification accuracy. We start by proposing a cheap pruning algorithm for f...

Overtting is a widely observed pathology of induction algorithms. For induction algorithms that build decision trees, pruning is a common approach to correct overtting. Most common pruning techniques , do not account for one potentially important factor | multiple comparisons. Multiple comparisons occur whenever an induction algorithm examines several candidate models and selects the one that b...