Mass Personalization google
Mass personalization is defined as custom tailoring by a company in accordance with its end users tastes and preferences. From collaborative engineering perspective, mass customization can be viewed as collaborative efforts between customers and manufacturers, who have different sets of priorities and need to jointly search for solutions that best match customers’ individual specific needs with manufacturers’ customization capabilities. The main difference between mass customization and mass personalization is that customization is the ability for a company to give its customers an opportunity to create and choose product to certain specifications, but does have limits. Clothing industry has also adopted the mass customization paradigm and some footwear retailers are producing mass customized shoes. The gaming market is seeing personalization in the new custom controller industry. A new, and notable, company called “Experience Custom” gives customers the opportunity to order personalized gaming controllers.
A website knowing a user’s location, and buying habits, will present offers and suggestions tailored to the user’s demographics; this is an example of mass personalization. The personalization is not individual but rather the user is first classified and then the personalization is based on the group they belong to. Behavioral targeting represents a concept that is similar to mass personalization. …


Deep Laplacian Pyramid Super-Resolution Network google
Convolutional neural networks have recently demonstrated high-quality reconstruction for single image super-resolution. However, existing methods often require a large number of network parameters and entail heavy computational loads at runtime for generating high-accuracy super-resolution results. In this paper, we propose the deep Laplacian Pyramid Super-Resolution Network for fast and accurate image super-resolution. The proposed network progressively reconstructs the sub-band residuals of high-resolution images at multiple pyramid levels. In contrast to existing methods that involve the bicubic interpolation for pre-processing (which results in large feature maps), the proposed method directly extracts features from the low-resolution input space and thereby entails low computational loads. We train the proposed network with deep supervision using the robust Charbonnier loss functions and achieve high-quality image reconstruction. Furthermore, we utilize the recursive layers to share parameters across as well as within pyramid levels, and thus drastically reduce the number of parameters. Extensive quantitative and qualitative evaluations on benchmark datasets show that the proposed algorithm performs favorably against the state-of-the-art methods in terms of run-time and image quality. …

Non-Parametric Generalized Linear Model (NP-GLM) google
In this paper, we try to solve the problem of temporal link prediction in information networks. This implies predicting the time it takes for a link to appear in the future, given its features that have been extracted at the current network snapshot. To this end, we introduce a probabilistic non-parametric approach, called ‘Non-Parametric Generalized Linear Model’ (NP-GLM), which infers the hidden underlying probability distribution of the link advent time given its features. We then present a learning algorithm for NP-GLM and an inference method to answer time-related queries. Extensive experiments conducted on both synthetic data and real-world Sina Weibo social network demonstrate the effectiveness of NP-GLM in solving temporal link prediction problem vis-a-vis competitive baselines. …

Advertisements