Genomic Prediction (GP) is the process of using genetic markers to predict complex traits. This process can accelerate the breeding cycle of crops and animals and if we interpret these models we can identify markers important for each trait. Many models have been used for GP; including linear models like ridge regression Best Linear Unbiased Prediction (rrBLUP) and various Bayesian models as well as nonlinear models such as decision tree based algorithms and Artificial Neural Networks (ANNs). The nonlinear models more accurately capture effects like epistasis and dominance which are important for predicting complex traits. With recent improvements in the field of deep learning, there has been interest in using these methods for GP. In this project, we use a deep learning method called Convolutional Neural Networks (CNNs) to predict the trait values of 18 different traits across 6 different species. CNNs are typically used for image classification due to their ability to identify complex spatial patterns. When used for GP, we hypothesize CNNs will identify complex genetic signatures associated with traits. To test this hypothesis we will compare the performance of our CNN models to the performance of other established methods such as rrBLUP and ANNs.