The past year or so has seen a true explosion in both the capabilities and adoption of artificial intelligence technologies. Today's generalized AI tools can solve specific problems more powerfully than the complex rule-based tools that preceded them. And, because these new AI tools can be deployed in many contexts, more and more applications and industries are ripe for transformation with AI technologies. By drawing from the best posts on the O'Reilly AI blog, this in-depth report summarizes the current state of AI technologies and applications, and provides useful guides to help you get started with deep learning and other AI tools.

With the widespread use of information technologies, information networks have increasingly become popular to capture complex relationships across various disciplines, such as social networks, citation networks, telecommunication networks, and biological networks. Analyzing these networks sheds light on different aspects of social life such as the structure of society, information diffusion, and different patterns of communication. However, the large scale of information networks often makes network analytic tasks computationally expensive and intractable. Recently, network representation learning has been proposed as a new learning paradigm that embeds network vertices into a low-dimensional vector space, by preserving network topology structure, vertex content, and other side information. This facilitates the original network to be easily handled in the new vector space for further analysis. In this survey, we perform a thorough review of the current literature on network representation learning in the field of data mining and machine learning. We propose a new categorization to analyze and summarize state-of-the-art network representation learning techniques according to the methodology they employ and the network information they preserve. Finally, to facilitate research on this topic, we summarize benchmark datasets and evaluation methodologies, and discuss open issues and future research directions in this field.

Nesterov's accelerated gradient descent (AGD), an instance of the general family of "momentum methods", provably achieves faster convergence rate than gradient descent (GD) in the convex setting. However, whether these methods are superior to GD in the nonconvex setting remains open. This paper studies a simple variant of AGD, and shows that it escapes saddle points and finds a second-order stationary point in $\tilde{O}(1/\epsilon^{7/4})$ iterations, faster than the $\tilde{O}(1/\epsilon^{2})$ iterations required by GD. To the best of our knowledge, this is the first Hessian-free algorithm to find a second-order stationary point faster than GD, and also the first single-loop algorithm with a faster rate than GD even in the setting of finding a first-order stationary point. Our analysis is based on two key ideas: (1) the use of a simple Hamiltonian function, inspired by a continuous-time perspective, which AGD monotonically decreases per step even for nonconvex functions, and (2) a novel framework called improve or localize, which is useful for tracking the long-term behavior of gradient-based optimization algorithms. We believe that these techniques may deepen our understanding of both acceleration algorithms and nonconvex optimization.

In this paper, we present a hybrid model that combines a neural conversational model and a rule-based graph dialogue system that assists users in scheduling reminders through a chat conversation. The graph based system has high precision and provides a grammatically accurate response but has a low recall. The neural conversation model can cater to a variety of requests, as it generates the responses word by word as opposed to using canned responses. The hybrid system shows significant improvements over the existing baseline system of rule based approach and caters to complex queries with a domain-restricted neural model. Restricting the conversation topic and combination of graph based retrieval system with a neural generative model makes the final system robust enough for a real world application.

In recent years numerous advanced malware, aka advanced persistent threats (APT) are allegedly developed by nation-states. The task of attributing an APT to a specific nation-state is extremely challenging for several reasons. Each nation-state has usually more than a single cyber unit that develops such advanced malware, rendering traditional authorship attribution algorithms useless. Furthermore, those APTs use state-of-the-art evasion techniques, making feature extraction challenging. Finally, the dataset of such available APTs is extremely small. In this paper we describe how deep neural networks (DNN) could be successfully employed for nation-state APT attribution. We use sandbox reports (recording the behavior of the APT when run dynamically) as raw input for the neural network, allowing the DNN to learn high level feature abstractions of the APTs itself. Using a test set of 1,000 Chinese and Russian developed APTs, we achieved an accuracy rate of 94.6%.

The OSTSC package is a powerful oversampling approach for classifying univariant, but multinomial time series data in R. This article provides a brief overview of the oversampling methodology implemented by the package. A tutorial of the OSTSC package is provided. We begin by providing three test cases for the user to quickly validate the functionality in the package. To demonstrate the performance impact of OSTSC, we then provide two medium size imbalanced time series datasets. Each example applies a TensorFlow implementation of a Long Short-Term Memory (LSTM) classifier - a type of a Recurrent Neural Network (RNN) classifier - to imbalanced time series. The classifier performance is compared with and without oversampling. Finally, larger versions of these two datasets are evaluated to demonstrate the scalability of the package. The examples demonstrate that the OSTSC package improves the performance of RNN classifiers applied to highly imbalanced time series data. In particular, OSTSC is observed to increase the AUC of LSTM from 0.543 to 0.784 on a high frequency trading dataset consisting of 30,000 time series observations.

Tensor completion is a problem of filling the missing or unobserved entries of partially observed tensors. Due to the multidimensional character of tensors in describing complex datasets, tensor completion algorithms and their applications have received wide attention and achievement in data mining, computer vision, signal processing, and neuroscience, etc. In this survey, we provide a modern overview of recent advances in tensor completion algorithms from the perspective of big data analytics characterized by diverse variety, large volume, and high velocity. Towards a better comprehension and comparison of vast existing advances, we summarize and categorize them into four groups including general tensor completion algorithms, tensor completion with auxiliary information (variety), scalable tensor completion algorithms (volume) and dynamic tensor completion algorithms (velocity). Besides, we introduce their applications on real-world data-driven problems and present an open-source package covering several widely used tensor decomposition and completion algorithms. Our goal is to summarize these popular methods and introduce them to researchers for promoting the research process in this field and give an available repository for practitioners. In the end, we also discuss some challenges and promising research directions in this community for future explorations.

Deep learning methods have recently achieved great empirical success on machine translation, dialogue response generation, summarization, and other text generation tasks. At a high level, the technique has been to train end-to-end neural network models consisting of an encoder model to produce a hidden representation of the source text, followed by a decoder model to generate the target. While such models have significantly fewer pieces than earlier systems, significant tuning is still required to achieve good performance. For text generation models in particular, the decoder can behave in undesired ways, such as by generating truncated or repetitive outputs, outputting bland and generic responses, or in some cases producing ungrammatical gibberish. This paper is intended as a practical guide for resolving such undesired behavior in text generation models, with the aim of helping enable real-world applications.

Abstract--With the spreading prevalence of Big Data, many advances have recently been made in this field. Frameworks such as Apache Hadoop and Apache Spark have gained a lot of traction over the past decades and have become massively popular, especially in industries. It is becoming increasingly evident that effective big data analysis is key to solving artificial intelligence problems. Thus, a multi-algorithm library was implemented in the Spark framework, called MLlib. While this library supports multiple machine learning algorithms, there is still scope to use the Spark setup efficiently for highly timeintensive and computationally expensive procedures like deep learning. In this paper, we propose a novel framework that combines the distributive computational abilities of Apache Spark and the advanced machine learning architecture of a deep multilayer perceptron (MLP), using the popular concept of Cascade Learning. We conduct empirical analysis of our framework on two real world datasets. The results are encouraging and corroborate our proposed framework, in turn proving that it is an improvement over traditional big data analysis methods that use either Spark or Deep learning as individual elements. A. Overview I. INTRODUCTION With the amount of data growing at an exponential rate, it is necessary to develop tools that are able to harness that data and extract value from it.

Note: If you are looking for a review paper, this blog post is also available as an article on arXiv. Added derivations of AdaMax and Nadam. Gradient descent is one of the most popular algorithms to perform optimization and by far the most common way to optimize neural networks. At the same time, every state-of-the-art Deep Learning library contains implementations of various algorithms to optimize gradient descent (e.g. These algorithms, however, are often used as black-box optimizers, as practical explanations of their strengths and weaknesses are hard to come by.