Cash is getting less attention and people are looking forward to paying companies with mobile apps and other technologies instead, according to a new survey by online invoicing and payment firm Viewpost, which surveyed 1,000 U.S consumers for its analysis. More than half of respondents say payments between companies and customers will soon be done through mobile apps. Only 11 percent of Americans think companies will bill them by paper in the future, and 54 percent believe companies will bill customers through automatic payments from their bank account or credit card. "People are willing to embrace a more convenient, frictionless payments future," Viewpost CEO Max Eliscu said in a released statement. Electronic payments are already popular today, with services like PayPal, Apple Pay, Android Pay and apps like Venmo.

Since we will be using scientific computing and machine learning packages at some point, I suggest that you install Anaconda. This actually is a reflection of the field of machine learning, since much of what data scientists do involves using machine learning algorithms to varying degrees. Gaining an intimate understanding of machine learning algorithms is beyond the scope of this article, and generally requires substantial amounts of time investment in a more academic setting, or via intense self-study at the very least. For example, when you come across an exercise implementing a regression model below, read the appropriate regression section of Ng's notes and/or view Mitchell's regression videos at that time.

Which authors of this paper are endorsers? Disable MathJax (What is MathJax?)

With ever-growing amount of data produced by the Internet of Things, there is a need for a "smart" engine to analyze it and drive valuable insights. Outlining the challenges, this blog post highlights the six stages of an IoT workflow where artificial intelligence can help out. A scary rate of IoT data growth The Internet of Things (IoT) is covering the gamut of industries: healthcare, aviation…www.altoros.com

The state-of-the-art named entity recognition (NER) systems are statistical machine learning models that have strong generalization capability (i.e., can recognize unseen entities that do not appear in training data) based on lexical and contextual information. However, such a model could still make mistakes if its features favor a wrong entity type. In this paper, we utilize Wikipedia as an open knowledge base to improve multilingual NER systems. Central to our approach is the construction of high-accuracy, high-coverage multilingual Wikipedia entity type mappings. These mappings are built from weakly annotated data and can be extended to new languages with no human annotation or language-dependent knowledge involved. Based on these mappings, we develop several approaches to improve an NER system. We evaluate the performance of the approaches via experiments on NER systems trained for 6 languages. Experimental results show that the proposed approaches are effective in improving the accuracy of such systems on unseen entities, especially when a system is applied to a new domain or it is trained with little training data (up to 18.3 F1 score improvement).

Variational inference methods often focus on the problem of efficient model optimization, with little emphasis on the choice of the approximating posterior. In this paper, we review and implement the various methods that enable us to develop a rich family of approximating posteriors. We show that one particular method employing transformations on distributions results in developing very rich and complex posterior approximation. We analyze its performance on the MNIST dataset by implementing with a Variational Autoencoder and demonstrate its effectiveness in learning better posterior distributions.

Deep neural networks (DNNs) have excellent representative power and are state of the art classifiers on many tasks. However, they often do not capture their own uncertainties well making them less robust in the real world as they overconfidently extrapolate and do not notice domain shift. Gaussian processes (GPs) with RBF kernels on the other hand have better calibrated uncertainties and do not overconfidently extrapolate far from data in their training set. However, GPs have poor representational power and do not perform as well as DNNs on complex domains. In this paper we show that GP hybrid deep networks, GPDNNs, (GPs on top of DNNs and trained end-to-end) inherit the nice properties of both GPs and DNNs and are much more robust to adversarial examples. When extrapolating to adversarial examples and testing in domain shift settings, GPDNNs frequently output high entropy class probabilities corresponding to essentially "don't know". GPDNNs are therefore promising as deep architectures that know when they don't know.

Deep learning massive success in almost every fields represents its ability to solve complex problems. The tradeoff between model complexity and accuracy is an important area of deep learning research. Very complex model with millions of parameters [8], [9] proved to the state of the art solution for many vision and natural language problems. A common way to measure the performance or generalizability of a deep learning model is to test it on a well discriminative validation/test set representing the variation of samples of the corresponding problem. Learning very complex model is a matter of the requirements of high computing power and huge dataset.

This paper considers the multi-armed thresholding bandit problem -- identifying all arms whose expected rewards are above a predefined threshold via as few pulls (or rounds) as possible -- proposed by Locatelli et al. [2016] recently. Although the proposed algorithm in Locatelli et al. [2016] achieves the optimal round complexity in a certain sense, there still remain unsolved issues. This paper proposes an asynchronous parallel thresholding algorithm and its parameter-free version to improve the efficiency and the applicability. On one hand, the proposed two algorithms use the empirical variance to guide the pull decision at each round, and significantly improve the round complexity of the "optimal" algorithm when all arms have bounded high order moments. The proposed algorithms can be proven to be optimal. On the other hand, most bandit algorithms assume that the reward can be observed immediately after the pull or the next decision would not be made before all rewards are observed. Our proposed asynchronous parallel algorithms allow making the choice of the next pull with unobserved rewards from earlier pulls, which avoids such an unrealistic assumption and significantly improves the identification process. Our theoretical analysis justifies the effectiveness and the efficiency of proposed asynchronous parallel algorithms.

The estimation of probabilities of network edges from the observed adjacency matrix has important applications to predicting missing links and network denoising. It has usually been addressed by estimating the graphon, a function that determines the matrix of edge probabilities, but this is ill-defined without strong assumptions on the network structure. Here we propose a novel computationally efficient method, based on neighborhood smoothing to estimate the expectation of the adjacency matrix directly, without making the structural assumptions that graphon estimation requires. The neighborhood smoothing method requires little tuning, has a competitive mean-squared error rate, and outperforms many benchmark methods on link prediction in simulated and real networks.