In this study, a hybrid technique is designed for classification of leukemia gene data by combining two classifiers namely, Input Discretized Neural Network (IDNN) and Genetic Algorithm-based Neural Network (GANN). The leukemia microarray gene expression data is preprocessed using probabilistic principal component analysis for dimension reduction. The dimension reduced data is subjected to two classifiers: first, an input discretized neural network and second, genetic algorithm-based neural network. In input discretized neural network, fuzzy logic is used to discretize the gene data using linguistic labels. The discretized input is used to train the neural network. The genetic algorithm-based neural network involves feature selection. The subset of genes is selected by evaluating fitness for each chromosome (solution). The subset of features with maximum fitness is used to train the neural network. The hybrid classifier designed, is experimented with the test data by subjecting it to both the trained neural networks simultaneously. The hybrid classifier employs a distance based classification that utilizes a mathematical model to predict the class type. The model utilizes the output values of IDNN and GANN with respect to the distances between the output and the median threshold, thereby predicting the class type. The performance of the hybrid classifier is compared with existing classification techniques such as neural network classifier, input discretized neural network and genetic algorithm-based neural network. The comparative result shows that the hybrid classifier technique obtains accuracy rate of 88.23% for leukemia gene data. © Maxwell Scientific Organization, 2015.