Biologically Inspired Tensor Features

According to the research results reported in the past decades, it is well acknowledged that face recognition is not a trivial task. With the development of electronic devices, we are gradually revealing the secret of object recognition in the primate's visual cortex. Therefore, it is time to reconsider face recognition by using biologically inspired features. In this paper, we represent face images by utilizing the C1 units, which correspond to complex cells in the visual cortex, and pool over S1 units by using a maximum operation to reserve only the maximum response of each local area of S1 units. The new representation is termed C1 Face. Because C1 Face is naturally a third-order tensor (or a three dimensional array), we propose three-way discriminative locality alignment (TWDLA), an extension of the discriminative locality alignment, which is a top-level discriminate manifold learning-based subspace learning algorithm. TWDLA has the following advantages: (1) it takes third-order tensors as input directly so the structure information can be well preserved; (2) it models the local geometry over every modality of the input tensors so the spatial relations of input tensors within a class can be preserved; (3) it maximizes the margin between a tensor and tensors from other classes over each modality so it performs well for recognition tasks and (4) it has no under sampling problem. Extensive experiments on YALE and FERET datasets show (1) the proposed C1Face representation can better represent face images than raw pixels and (2) TWDLA can duly preserve both the local geometry and the discriminative information over every modality for recognition.

Semisupervised Dimensionality Reduction and Classification Through Virtual Label Regression

Semisupervised dimensionality reduction has been attracting much attention as it not only utilizes both labeled and unlabeled data simultaneously, but also works well in the situation of out-of-sample. This paper proposes an effective approach of semisupervised dimensionality reduction through label propagation and label regression. Different from previous efforts, the new approach propagates the label information from labeled to unlabeled data with a well-designed mechanism of random walks, in which outliers are effectively detected and the obtained virtual labels of unlabeled data can be well encoded in a weighted regression model. These virtual labels are thereafter regressed with a linear model to calculate the projection matrix for dimensionality reduction. By this means, when the manifold or the clustering assumption of data is satisfied, the labels of labeled data can be correctly propagated to the unlabeled data; and thus, the proposed approach utilizes the labeled and the unlabeled data more effectively than previous work. Experimental results are carried out upon several databases, and the advantage of the new approach is well demonstrated.

Fast Haar Transform Based Feature Extraction for Face Representation and Recognition

Subspace learning is the process of finding a proper feature subspace and then projecting high-dimensional data onto the learned low-dimensional subspace. The projection operation requires many floating-point multiplications and additions, which makes the projection process computationally expensive. To tackle this problem, this paper proposes two simple-but-effective fast subspace learning and image projection methods, fast Haar transform (FHT) based principal component analysis and FHT based spectral regression discriminant analysis. The advantages of these two methods result from employing both the FHT for subspace learning and the integral vector for feature extraction. Experimental results on three face databases demonstrated their effectiveness and efficiency.

吗啡奖赏效应及其敏化与空间学习能力的关系

Rewarding experience after drug use is one of the mechanisms of substance abuse. Previous evidence indicated that rewarding experience was closely related to learning processes. Neuroscience studies have already established multiple-mode learning model. Reference memory system and habit memory are associated with hippocampus and dorsa striatum respectively, which are also involved in the rewarding effect of morphine. However, the relationship between spatial/habit learning and morphine reward property is still unclear. After drug use, with sensitization to rewarding effect, spatial learning is also changed. To study the mechanism of increment of spatial learning would provide new perspective about reward learning. Based on the individual difference between spatial learning and reward learning, the experiments studied relationship between the two leaning abilities and tested the function of dorsal hippocampus and dorsal striatum in morphine-induced CPP. The results were summarized below： 1 In a single－rule learning water maze task, subjects better in spatial learning also excelled in rewarding learning. In a multi-rule learning task, morphine administration was more rewarding to subjects of use place strategy. 2 Treatment potentiating the rewarding effect of morphine also increased place-rule learning, with no significant improvement in habit learning. 3 Intracranial injections into CA1 of hippocampus or dorsal striatum of M1 antagonist, Pirenzepine, could block the establishment of morphine CPP after three days morphine treatment. In contrast, the antagonist of D1 receptor SCH23390 had no blocking effect. Both Pirenzepine and SCH23390 blocked the locomotor-stimulating effect of morphine. In summary, spatial learning stimulated the behavioral expression of morphine’s rewarding effect, in which CA1 of hippocampus was critically involved. On the other side, a pretreatment schedule of morphine, while increased the rewarding effect, improved place-rule learning, indicating that spatial learning might be one chain of sensitization to drug rewards effects