taxnodes:Technology: Overviews


Blog

#artificialintelligence

The Dragonfly Machine Learning Engine (MLE) provides the machine learning and data science capabilities included within OPNids. Data science and machine learning promise to counteract the dynamic threat environment created by growing network traffic and increasing threat actor sophistication. This post will provide an overview of the MLE engine itself, reasoning for why data science and cybersecurity go together, and some insight into using the MLE as part of the OPNids system. The Dragonfly MLE is available as part of OPNids. The Dragonfly MLE provides a powerful framework for deploying anomaly detection algorithms, threat intelligence lookups, and machine learning predictions within a network security infrastructure.


Fleets using AI to accelerate safety, efficiency

#artificialintelligence

"Artificial intelligence" (AI) may evoke fears of robots writing their own software code and not taking orders from humans. The real AI, at least in present form, is delivering results in the business world. Technology companies are using powerful computers and advanced statistical models to accelerate their product development. Most are not calling these efforts AI but rather machine learning. As a form of AI, machine learning is making it possible to quickly find relevant patterns in data captured by Internet of Things (IoT) devices and sensors, explains Adam Kahn, vice president of fleets for Netradyne, which has a vision-based fleet safety system called Driveri ("driver eye").


A Survey on Methods and Theories of Quantized Neural Networks

arXiv.org Machine Learning

Deep neural networks are the state-of-the-art methods for many real-world tasks, such as computer vision, natural language processing and speech recognition. For all its popularity, deep neural networks are also criticized for consuming a lot of memory and draining battery life of devices during training and inference. This makes it hard to deploy these models on mobile or embedded devices which have tight resource constraints. Quantization is recognized as one of the most effective approaches to satisfy the extreme memory requirements that deep neural network models demand. Instead of adopting 32-bit floating point format to represent weights, quantized representations store weights using more compact formats such as integers or even binary numbers. Despite a possible degradation in predictive performance, quantization provides a potential solution to greatly reduce the model size and the energy consumption. In this survey, we give a thorough review of different aspects of quantized neural networks. Current challenges and trends of quantized neural networks are also discussed.


A Review of Learning with Deep Generative Models from perspective of graphical modeling

arXiv.org Machine Learning

This document aims to provide a review on learning with deep generative models (DGMs), which is an highly-active area in machine learning and more generally, artificial intelligence. This review is not meant to be a tutorial, but when necessary, we provide self-contained derivations for completeness. This review has two features. First, though there are different perspectives to classify DGMs, we choose to organize this review from the perspective of graphical modeling, because the learning methods for directed DGMs and undirected DGMs are fundamentally different. Second, we differentiate model definitions from model learning algorithms, since different learning algorithms can be applied to solve the learning problem on the same model, and an algorithm can be applied to learn different models. We thus separate model definition and model learning, with more emphasis on reviewing, differentiating and connecting different learning algorithms. We also discuss promising future research directions. This review is by no means comprehensive as the field is evolving rapidly. The authors apologize in advance for any missed papers and inaccuracies in descriptions. Corrections and comments are highly welcome.


Kernel Flows: from learning kernels from data into the abyss

arXiv.org Machine Learning

Learning can be seen as approximating an unknown function by interpolating the training data. Kriging offers a solution to this problem based on the prior specification of a kernel. We explore a numerical approximation approach to kernel selection/construction based on the simple premise that a kernel must be good if the number of interpolation points can be halved without significant loss in accuracy (measured using the intrinsic RKHS norm $\|\cdot\|$ associated with the kernel). We first test and motivate this idea on a simple problem of recovering the Green's function of an elliptic PDE (with inhomogeneous coefficients) from the sparse observation of one of its solutions. Next we consider the problem of learning non-parametric families of deep kernels of the form $K_1(F_n(x),F_n(x'))$ with $F_{n+1}=(I_d+\epsilon G_{n+1})\circ F_n$ and $G_{n+1} \in \operatorname{Span}\{K_1(F_n(x_i),\cdot)\}$. With the proposed approach constructing the kernel becomes equivalent to integrating a stochastic data driven dynamical system, which allows for the training of very deep (bottomless) networks and the exploration of their properties. These networks learn by constructing flow maps in the kernel and input spaces via incremental data-dependent deformations/perturbations (appearing as the cooperative counterpart of adversarial examples) and, at profound depths, they (1) can achieve accurate classification from only one data point per class (2) appear to learn archetypes of each class (3) expand distances between points that are in different classes and contract distances between points in the same class. For kernels parameterized by the weights of Convolutional Neural Network, minimizing approximation errors incurred by halving random subsets of interpolation points, appears to outperform training (the same CNN architecture) with relative entropy and dropout.


How do chatbots work? An overview of the architecture of a chatbot

#artificialintelligence

Humans are constantly fascinated with auto-operating AI-driven gadgets. The latest trend that is catching the eye of the majority of the tech industry is chatbots. And with so much research and advancement in the field, the programming is winding up more human-like, on top of being automated. The blend of immediate response reaction and consistent connectivity makes them an engaging change to the web applications trend. In general terms, a bot is nothing but a software that will perform automatic tasks.


Artificial Intelligence in HR – FAQs you need to be able to answer – TI People

#artificialintelligence

On the second level of artificial intelligence networked machines can develop new models and algorithms ad hoc. In HR this technology can improve the preselection of applicants. With this second stage of artificial intelligence we can tackle an imminent and important problem of employee selection today: Unconscious prejudices. The world is full of it, as well as the world of employee selection: As a rule, people prefer "themselves and their peers" to people who are socialized differently. Personal experience with certain behaviors of others also determines a person s judgement of others.


Interpretable Time Series Classification using All-Subsequence Learning and Symbolic Representations in Time and Frequency Domains

arXiv.org Machine Learning

The time series classification literature has expanded rapidly over the last decade, with many new classification approaches published each year. The research focus has mostly been on improving the accuracy and efficiency of classifiers, while their interpretability has been somewhat neglected. Classifier interpretability has become a critical constraint for many application domains and the introduction of the 'right to explanation' GDPR EU legislation in May 2018 is likely to further emphasize the importance of explainable learning algorithms. In this work we analyse the state-of-the-art for time series classification, and propose new algorithms that aim to maintain the classifier accuracy and efficiency, but keep interpretability as a key design constraint. We present new time series classification algorithms that advance the state-of-the-art by implementing the following three key ideas: (1) Multiple resolutions of symbolic approximations: we combine symbolic representations obtained using different parameters; (2) Multiple domain representations: we combine symbolic approximations in time (e.g., SAX) and frequency (e.g., SFA) domains; (3) Efficient navigation of a huge symbolic-words space: we adapt a symbolic sequence classifier named SEQL, to make it work with multiple domain representations (e.g., SAX-SEQL, SFA-SEQL), and use its greedy feature selection strategy to effectively filter the best features for each representation. We show that a multi-resolution multi-domain linear classifier, SAX-SFA-SEQL, achieves a similar accuracy to the state-of-the-art COTE ensemble, and to a recent deep learning method (FCN), but uses a fraction of the time required by either COTE or FCN. We discuss the accuracy, efficiency and interpretability of our proposed algorithms. To further analyse the interpretability aspect of our classifiers, we present a case study on an ecology benchmark.


Robust high dimensional factor models with applications to statistical machine learning

arXiv.org Machine Learning

Factor models are a class of powerful statistical models that have been widely used to deal with dependent measurements that arise frequently from various applications from genomics and neuroscience to economics and finance. As data are collected at an ever-growing scale, statistical machine learning faces some new challenges: high dimensionality, strong dependence among observed variables, heavy-tailed variables and heterogeneity. High-dimensional robust factor analysis serves as a powerful toolkit to conquer these challenges. This paper gives a selective overview on recent advance on high-dimensional factor models and their applications to statistics including Factor-Adjusted Robust Model selection (FarmSelect) and Factor-Adjusted Robust Multiple testing (FarmTest). We show that classical methods, especially principal component analysis (PCA), can be tailored to many new problems and provide powerful tools for statistical estimation and inference. We highlight PCA and its connections to matrix perturbation theory, robust statistics, random projection, false discovery rate, etc., and illustrate through several applications how insights from these fields yield solutions to modern challenges. We also present far-reaching connections between factor models and popular statistical learning problems, including network analysis and low-rank matrix recovery.


Grassmannian Learning: Embedding Geometry Awareness in Shallow and Deep Learning

arXiv.org Machine Learning

Modern machine learning algorithms have been adopted in a range of signal-processing applications spanning computer vision, natural language processing, and artificial intelligence. Many relevant problems involve subspace-structured features, orthogonality constrained or low-rank constrained objective functions, or subspace distances. These mathematical characteristics are expressed naturally using the Grassmann manifold. Unfortunately, this fact is not yet explored in many traditional learning algorithms. In the last few years, there have been growing interests in studying Grassmann manifold to tackle new learning problems. Such attempts have been reassured by substantial performance improvements in both classic learning and learning using deep neural networks. We term the former as shallow and the latter deep Grassmannian learning. The aim of this paper is to introduce the emerging area of Grassmannian learning by surveying common mathematical problems and primary solution approaches, and overviewing various applications. We hope to inspire practitioners in different fields to adopt the powerful tool of Grassmannian learning in their research.