Could a training example be detrimental to learning? Contrary to the common belief that more training data is needed for better generalization, we show that the learning algorithm might be better off when some training examples are discarded. In other words, the quality of the examples matters. We explore a general approach to identify examples that are troublesome for learning with a given mod...

Determining the architecture of a neural network is an important issue for any learning task. For recurrent neural networks no general methods exist that permit the estimation of the number of layers of hidden neurons, the size of layers or the number of weights. We present a simple pruning heuristic that significantly improves the generalization performance of trained recurrent networks. We il...

A new supervised learning procedure for training RBF networks is proposed. It uses a pair of parallel running Kalman filters to sequentially update both the output weights and the centers of the network. The method offers advantages over the joint parameters vector approach in terms of memory requirements and training time. Simulation results for chaotic time series prediction and the 2-spirals...

An efficient decoding algorithm for segmental HMMs (SHMMs) is proposed with multi-stage pruning. The generation by SHMMs of a feature trajectory for each state expands the search space and the computational cost of decoding. It is reduced in three ways: pre-cost partitioning, start-node (SN) beam pruning, and conventional endnode (EN) beam pruning. Experiments show that partitioning cuts comput...

With the rapid growth of online text information, efficient text classification has become one of the key techniques for organizing and processing text repositories. In this paper, an efficient text classification approach was proposed based on pruning training-corpus. By using the proposed approach, noisy and superfluous documents in training corpuses can be cut off drastically, which leads to...

in this research the possibility of vine pruning fibers in combination with wood fibers was studied in order to fabricate medium density fiberboard. vine pruning fibers content in three levels of 0/100, 30/70 and 60/40 (weight percent) and press time in three levels of 4, 5 and 6 minutes were as variable factors. one layer panels with a density of 0.65 g/cm3 and thickness of 15 mm were made. th...

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...