Semantic scene classification, robotic state recognition, and many other real-world applications involve multilabel classification with imbalanced data. In this paper, we address these problems by using an enrichment process in neural net training. The enrichment process can manage the imbalanced data and train the neural net with high classification accuracy. Experimental results on a robotic arm controller show that our method has better generalization performance than traditional neural net training in solving the multi-label and imbalanced data problems.

No abstract

Facial image associative memory takes a facial input image and returns associated faces pre-embedded in memory. This paper proposes a three-phase implementation process: a) sensory pre-processing, b) information interfusion, and c) association with existing faces. This paper reports on the simulation and performance of the proposed first phase, sensory preprocessing, based on multiple neural network structures to translate image sensory pre-processing into transformed information. The multi-network structure is tested by 46 faces of 21 individuals. The result shows the first phase can produce acceptable associations at 89.1% of all test faces with less than 0.02 energy error at above 0.60 facial image pixel-based correlation (closeness).

In the conventional eigenface method, the princi-One of many important issues in face recognition is to seple component analysis (PCA) algorithm associates the Eigen lect efficient facial image representations. Among appearancevectors with the changes in illumination. In this paper, we based facial image representations, eigenfaces [5], [6], fisherpropose an improvement of facial image association for face f recognition using a cognitive processing model. This method faces [5], [7], and gaborfaces [8] have proved to be effective is based on the notion of multiple-phase associative memory. on large databases. Principle component analysis (PCA) [6], The Essex face database is used to verify our model for facial independent component analysis (ICA) [9], and linear disimage recognition and compare the results of face recognition criminant analysis (LDA) [7] perform statistical dimensional with conventional eigenface method. The simulation results show reduction to capture the de-cofrelation among stored images.that the proposed cognitive processing model approach results

No abstract