The IceCube Neutrino Observatory observes neutrinos interacting deep within the South Pole ice. It consists of 5,160 digital optical modules, which are embedded within a cubic kilometer of ice, over depths of 1,450 m to 2,450 m. At the lower center of the array is the DeepCore subdetector. Its denser sensor configuration lowers the observable energy threshold to the GeV-scale, facilitating the study of atmospheric neutrino oscillations. The precise reconstruction of neutrino direction is critical in the measurements of oscillation parameters. This work presents a method to reconstruct the zenith angle of GeV-scale events in IceCube by using a convolutional neural network and compares the result to that of the current likelihood-based reconstruction algorithm.