Recently the deep learning has shown its advantage in representation and clustering for time series data. Despite considerable progress, existing approaches mostly seek to train neural network by some instance reconstruction based or cluster distribution objective, which, however, lack ability exploit sample-wise (or augmentation-wise) contrastive information even higher-level (e.g., cluster-le...

In conventional recognition tasks, models are only trained to recognize learned targets, but it is usually difficult collect training examples of all potential categories. the testing phase, when receive test samples from unknown classes, they mistakenly classify into known classes. Open set (OSR) a more realistic task, which requires classifier detect while keeping high classification accuracy...

Deep clustering has attracted increasing attention in recent years due to its capability of joint representation learning and via deep neural networks. In latest developments, the contrastive emerged as an effective technique substantially enhance performance. However, existing based algorithms mostly focus on some carefully-designed augmentations (often with limited transformations preserve st...

Contrastive Divergence (CD) and Persistent Contrastive Divergence (PCD) are popular methods for training Restricted Boltzmann Machines. However, both methods use an approximate method for sampling from the model distribution. As a side effect, these approximations yield significantly different biases and variances for stochastic gradient estimates of individual data points. It is well known tha...

In this study we show that constituency is of limited importance for a proper treatment of the interaction between the linear position of a wa-marked nominal in a Japanese sentence and possible domains of contrastive focus, and that constraints concerning contrastive focus should be represented in terms of linear order and not constituency. Linearisation HPSG, where linear order is independent ...

The idea of contrast plays an important role in the analysis of information structure and discourse structure. In the literature on information structure, we encounter the concept of contrastive focus and of contrastive topic, and there is also the opinion that focus in general establishes a contrast. In the literature on discourse structure, it is commonly held that there is a discourse relati...

This study explores prosodic strengthening in the production of fortis plosives in Italian as a function of four structural levels of prominence, reflecting differing focal conditions (in order of increasing prominence: postfocal, broad focus, narrow focus and contrastive narrow focus). The overall analysis indicated that for lingual consonants closure duration was the most important acoustic p...

We present a novel class of learning algorithms for undirected graphical models, based on the contrastive free energy (CF). In particular we study the naive mean field, TAP and Bethe approximations to the contrastive free energy. The main advantage of CFlearning is the fact that it eliminates the need to infer equilibrium statistics for which mean field type approximations are particularly unsu...