microRNAs (miRNAs) are a major type of small RNA that alter gene expression at the posttranscriptional or translational level. They have been shown to play important roles in a wide range of biological processes. Many computational methods have been developed to predict targets of miRNAs in order to understand miRNAs' function. However, the majority of the methods depend on a set of predefined features that require considerable effort and resources to compute, and these methods often do not effectively on the prediction of miRNA targets. Therefore, we developed a novel hybrid deep learningbased approach that is capable to predict miRNA targets at a higher accuracy. Our approach integrates two deep learning methods: convolutional neural networks (CNNs) that excel in learning spatial features, and recurrent neural networks (RNNs) that discern sequential features. By combining CNNs and RNNs, our approach has the advantages of learning both the intrinsic spatial and sequential features of miRNA:target. The inputs for the approach are raw sequences of miRNA and gene sequences. Data from two latest miRNA target prediction studies were used in our study: the DeepMirTar dataset and the miRAW dataset. Two models were obtained by training on the two datasets separately. The models achieved a higher accuracy than the methods developed in the previous studies: 0.9787 vs. 0.9348 for the DeepMirTar dataset; 0.9649 vs. 0.935 for the miRAW dataset. We also calculated a series of model evaluation metrics including sensitivity, specificity, F-score and Brier Score. Our approach consistently outperformed the current methods. In addition, we compared our approach with earlier developed deep learning methods, resulting in an overall better performance. Lastly, a unified model for both datasets was developed with an accuracy of 0.9545. We named the unified model miTAR for miRNA target prediction. The source code and executable are available at https://github.com/tjgu/miTAR. Advances in our understanding of the interactions between miRNAs and their targets has led to the development of many computational methods/tools to predict miRNA targets. The majority of these tools are based on common features of the miRNA:target interaction. Four features are widely used: sequence complement (especially in the seed region that is generally defined as a 6 or 7 nts sequence starting at the second or third nucleotide(nt) of the miRNA sequence), thermodynamic stability, target site accessibility and sequence conservation among species (Peterson, et al., 2014). Several widely used tools have been developed based on these features. For example, miRanda (Enright, et al., 2003) relies on sequence complementarity and binding energy; TargetScanS (Lewis, et al., 2005) relies on sequence complementarity in seed region; while PITA (Kertesz, et al., 2007) relies on target site accessibility. However, miRNA targets predicted by different methods and tools are inconsistent with one another. Furthermore, using known features limits the ability to predict novel o...