Processamento da rede neocognitron para reconhecimento facial em ambiente de alto desempenho GPU

Abstract

This work presents an implementation of the Neocognitron Neural Network, using a high performance computing architecture based on GPU (Graphics Processing Unit). Neocognitron is an artificial neural network, proposed by Fukushima and collaborators, constituted of several hierarchical stages of neuron layers, organized in two-dimensional matrices called cellular plains. For the high performance computation of Face Recognition application using Neocognitron it was used CUDA (Compute Unified Device Architecture) as API (Application Programming Interface) between the CPU and the GPU, from GeForce 8800 GTX of NVIDIA company, with 128 ALU s. As face image databases it was used a face database created at UFSCar, and the CMU-PIE (Carnegie Melon University - Pose, Illumination, and Expression) database. The load balancing through the parallel processing architecture was obtained by means of the distributed processing of the cellular connections as threads organized in blocks, following the CUDA philosophy of development. The results showed the viability of this type of device as a massively parallel data processing tool, and that smaller the granularity of the parallel processing, and the independence of the processing, better is its performance.