A novel neuroscience-inspired architecture: For computer vision applications

The theory behind deep learning, the human visual system was investigated and general principles of how it functions are extracted. Our finding is that there are neuroscience theories that are not utilized in deep learning. Therefore, in this work, a novel model utilizing some of those theories is developed. The new model addresses the parallel nature of the human brain compared to the hierarchal (serial) brain model that is followed by current deep learning systems. The validation of the proposed model was conducted using "Shape" feature dimension. The results show up to 2% accuracy rate compared to our implementation of DeepFace, a high performing face recognition algorithm that was developed by Facebook, is achieved under the same hardware/ software conditions; and we were able to speed up the training up to 21% per a training patch compared to DeepFace.