A method of principal component analysis (PCA) based on a new L1-norm optimization technique is proposed. Unlike conventional PCA which is based on L2-norm, the proposed method is robust to outliers because it utilizes L1-norm which is less sensitive to outliers. It is invariant to rotations as well. The proposed L1-norm optimization technique is intuitive, simple, and easy to implement. It is also proven to find a locally maximal solution. The proposed method is applied to several datasets and the performances are compared with those of other conventional methods.

Feature selection plays an important role in classifying systems such as neural networks (NNs). We use a set of attributes which are relevant, irrelevant or redundant and from the viewpoint of managing a dataset which can be huge, reducing the number of attributes by selecting only the relevant ones is desirable. In doing so, higher performances with lower computational effort is expected. In this paper, we propose two feature selection algorithms. The limitation of mutual information feature selector (MIFS) is analyzed and a method to overcome this limitation is studied. One of the proposed algorithms makes more considered use of mutual information between input attributes and output classes than the MIFS. What is demonstrated is that the proposed method can provide the performance of the ideal greedy selection algorithm when information is distributed uniformly. The computational load for this algorithm is nearly the same as that of MIFS. In addition, another feature selection algorithm using the Taguchi method is proposed. This is advanced as a solution to the question as to how to identify good features with as few experiments as possible. The proposed algorithms are applied to several classification problems and compared with MIFS. These two algorithms can be combined to complement each other's limitations. The combined algorithm performed well in several experiments and should prove to be a useful method in selecting features for classification problems.

Mutual information is a good indicator of relevance between variables, and have been used as a measure in several feature selection algorithms. However, calculating the mutual information is difficult, and the performance of a feature selection algorithm depends on the accuracy of the mutual information. In this paper, we propose a new method of calculating mutual information between input and class variables based on the Parzen window, and we apply this to a feature selection algorithm for classification problems.

We investigate the design aspects of feature distillation methods achieving network compression and propose a novel feature distillation method in which the distillation loss is designed to make a synergy among various aspects: teacher transform, student transform, distillation feature position and distance function. Our proposed distillation loss includes a feature transform with a newly designed margin ReLU, a new distillation feature position, and a partial L 2 distance function to skip redundant information giving adverse effects to the compression of student. In Ima-geNet, our proposed method achieves 21.65% of top-1 error with ResNet50, which outperforms the performance of the teacher network, ResNet152. Our proposed method is evaluated on various tasks such as image classification, object detection and semantic segmentation and achieves a significant performance improvement in all tasks. The code is available at bhheo.github.io/overhaul * This work was done when authors were in research internship at Clova AI Research, NAVER corp. 78.31 Teacher (ResNet152) 1 arXiv:1904.01866v2 [cs.CV] 9 Aug 2019 T t T s T t T s d d Training image Y t Y s T t T s d Teacher network Student network Figure 2. The general training scheme of feature distillation. The form of teacher transform Tt, student transform Ts and distance d differ from method to method.

Sentence matching is widely used in various natural language tasks such as natural language inference, paraphrase identification, and question answering. For these tasks, understanding logical and semantic relationship between two sentences is required but it is yet challenging. Although attention mechanism is useful to capture the semantic relationship and to properly align the elements of two sentences, previous methods of attention mechanism simply use a summation operation which does not retain original features enough. Inspired by DenseNet, a densely connected convolutional network, we propose a densely-connected co-attentive recurrent neural network, each layer of which uses concatenated information of attentive features as well as hidden features of all the preceding recurrent layers. It enables preserving the original and the co-attentive feature information from the bottommost word embedding layer to the uppermost recurrent layer. To alleviate the problem of an ever-increasing size of feature vectors due to dense concatenation operations, we also propose to use an autoencoder after dense concatenation. We evaluate our proposed architecture on highly competitive benchmark datasets related to sentence matching. Experimental results show that our architecture, which retains recurrent and attentive features, achieves state-of-the-art performances for most of the tasks.