Most people think they know what the term "artificial intelligence" means, based on the results of a survey Pegasystems released Tuesday. However, their responses suggested that they probably don't fully understand how it's being used today, including in the customer service realm. Researchers polled 6,000 adult consumers in the United States, the UK, the Netherlands, France and Germany. Seventy-two percent of the survey participants said they understood what was meant by "artificial intelligence." While 32 percent said they weren't sure if they had interacted with AI, 34 percent said they had.

The Long Short-Term Memory recurrent neural network has the promise of learning long sequences of observations. It seems a perfect match for time series forecasting, and in fact, it may be. In this tutorial, you will discover how to develop an LSTM forecast model for a one-step univariate time series forecasting problem. Time Series Forecasting with the Long Short-Term Memory Network in Python Photo by Matt MacGillivray, some rights reserved. This is a big topic and we are going to cover a lot of ground. This tutorial assumes you have a Python SciPy environment installed. You can use either Python 2 or 3 with this tutorial. You must have Keras (2.0 or higher) installed with either the TensorFlow or Theano backend.

Artificial intelligence will be the main way that banks interact with their customers within the next three years, a report from consultancy Accenture has suggested. Banks such as Royal Bank of Scotland (RBS) are increasingly using chatbots to answer customer queries. The report examined the views of 600 bankers and other experts. Many, perhaps ironically, felt that AI would help banks create a more human-like customer experience. "The big paradox here is that people think technology will lead to banking becoming more and more automated and less and less personalised, but what we've seen coming through here is the view that technology will actually help banking become a lot more personalised," said Alan McIntyre, head of the Accenture's banking practice and co-author of the report, Banking Technology Vision 2017.

Given a set of items of unknown utility, we need to select one with a utility as high as possible ("the selection problem"). Measurements (possibly noisy) of item values prior to selection are allowed, at a known cost. The goal is to optimize the overall sequential decision process of measurements and selection. Value of information (VOI) is a well-known scheme for selecting measurements, but the intractability of the problem typically leads to using myopic VOI estimates. Other schemes have also been proposed, some with approximation guarantees, based on submodularity criteria. However, it was observed that the VOI is not submodular in general. In this paper we examine theoretical properties of VOI for the selection problem, and identify cases of submodularity and supermodularity. We suggest how to use these properties to compute approximately optimal measurement batch policies, with an example based on a "wine selection problem".

In this paper, we introduce an algorithm for performing spectral clustering efficiently. Spectral clustering is a powerful clustering algorithm that suffers from high computational complexity, due to eigen decomposition. In this work, we first build the adjacency matrix of the corresponding graph of the dataset. To build this matrix, we only consider a limited number of points, called landmarks, and compute the similarity of all data points with the landmarks. Then, we present a definition of the Laplacian matrix of the graph that enable us to perform eigen decomposition efficiently, using a deep autoencoder. The overall complexity of the algorithm for eigen decomposition is $O(np)$, where $n$ is the number of data points and $p$ is the number of landmarks. At last, we evaluate the performance of the algorithm in different experiments.

This paper presents a Convolutional Neural Network (CNN) based page segmentation method for handwritten historical document images. We consider page segmentation as a pixel labeling problem, i.e., each pixel is classified as one of the predefined classes. Traditional methods in this area rely on carefully hand-crafted features or large amounts of prior knowledge. In contrast, we propose to learn features from raw image pixels using a CNN. While many researchers focus on developing deep CNN architectures to solve different problems, we train a simple CNN with only one convolution layer. We show that the simple architecture achieves competitive results against other deep architectures on different public datasets. Experiments also demonstrate the effectiveness and superiority of the proposed method compared to previous methods.

The ability of learning from noisy labels is very useful in many visual recognition tasks, as a vast amount of data with noisy labels are relatively easy to obtain. Traditionally, the label noises have been treated as statistical outliers, and approaches such as importance re-weighting and bootstrap have been proposed to alleviate the problem. According to our observation, the real-world noisy labels exhibit multi-mode characteristics as the true labels, rather than behaving like independent random outliers. In this work, we propose a unified distillation framework to use side information, including a small clean dataset and label relations in knowledge graph, to "hedge the risk" of learning from noisy labels. Furthermore, unlike the traditional approaches evaluated based on simulated label noises, we propose a suite of new benchmark datasets, in Sports, Species and Artifacts domains, to evaluate the task of learning from noisy labels in the practical setting. The empirical study demonstrates the effectiveness of our proposed method in all the domains.

In this paper, we determine the optimal convergence rates for strongly convex and smooth distributed optimization in two settings: centralized and decentralized communications over a network. For centralized (i.e. master/slave) algorithms, we show that distributing Nesterov's accelerated gradient descent is optimal and achieves a precision $\varepsilon > 0$ in time $O(\sqrt{\kappa_g}(1+\Delta\tau)\ln(1/\varepsilon))$, where $\kappa_g$ is the condition number of the (global) function to optimize, $\Delta$ is the diameter of the network, and $\tau$ (resp. $1$) is the time needed to communicate values between two neighbors (resp. perform local computations). For decentralized algorithms based on gossip, we provide the first optimal algorithm, called the multi-step dual accelerated (MSDA) method, that achieves a precision $\varepsilon > 0$ in time $O(\sqrt{\kappa_l}(1+\frac{\tau}{\sqrt{\gamma}})\ln(1/\varepsilon))$, where $\kappa_l$ is the condition number of the local functions and $\gamma$ is the (normalized) eigengap of the gossip matrix used for communication between nodes. We then verify the efficiency of MSDA against state-of-the-art methods for two problems: least-squares regression and classification by logistic regression.

Variance reduction (VR) methods boost the performance of stochastic gradient descent (SGD) by enabling the use of larger, constant stepsizes and preserving linear convergence rates. However, current variance reduced SGD methods require either high memory usage or an exact gradient computation (using the entire dataset) at the end of each epoch. This limits the use of VR methods in practical distributed settings. In this paper, we propose a variance reduction method, called VR-lite, that does not require full gradient computations or extra storage. We explore distributed synchronous and asynchronous variants that are scalable and remain stable with low communication frequency. We empirically compare both the sequential and distributed algorithms to state-of-the-art stochastic optimization methods, and find that our proposed algorithms perform favorably to other stochastic methods.

We study the problem of detecting a change in the mean of one-dimensional Gaussian process data. This problem is investigated in the setting of increasing domain (customarily employed in time series analysis) and in the setting of fixed domain (typically arising in spatial data analysis). We propose a detection method based on the generalized likelihood ratio test (GLRT), and show that our method achieves nearly asymptotically optimal rate in the minimax sense, in both settings. The salient feature of the proposed method is that it exploits in an efficient way the data dependence captured by the Gaussian process covariance structure. When the covariance is not known, we propose the plug-in GLRT method and derive conditions under which the method remains asymptotically near optimal. By contrast, the standard CUSUM method, which does not account for the covariance structure, is shown to be asymptotically optimal only in the increasing domain. Our algorithms and accompanying theory are applicable to a wide variety of covariance structures, including the Matern class, the powered exponential class, and others. The plug-in GLRT method is shown to perform well for maximum likelihood estimators with a dense covariance matrix.