Eye-tracking has become a significant tool in various areas, incorporating interaction of humans with a computer, computer vision, psychology, and medical diagnostics. Various protocols have been utilized to track the gaze. Although, some may not be accurate in the real world, while others may need explicit custom calibration, which can cause problems. Few of these techniques are associated with low image grades and varying lighting situations. The latest success and popularity of deep studying has dramatically increased the effectiveness of eye-tracking. The convenience of huge datasets additionally improves the function of deep learning-depend techniques. This technical paper introduces the latest deep studying-depend gaze assessment technology with a concentration on Fully Convolution Neural Networks (FCNN). This technical paper also gives an overview of other machine-based eye assessment methods. This research objective to enable the research population to generate significant and useful horizons that can improve the structure and growth of better, more effective deep learning depends on eye-tracking methods. This paper also gives information on different pertained models, network structures, and open origin datasets to help train deep learning models.