This talk was recorded in London on October 30th, 2018. Slides from the talk can be viewed here: https://www.slideshare.net/0xdata/nea... Session: Travelport is a leading travel commerce platform that has truly huge data and many complex needs in terms of processing, performance and latency. This talk will demonstrate how we were able to harness big data technologies, H2O and cloud integration to deploy AI at scale and at low latency. The talk to cover practical advice taken from our AI journey; you will learn the successful strategies and the pitfalls of near real-time retraining ML models with streaming data and using all opensource technologies. Bio: As principal data scientist at Travelport, Levi Brackman leads a team of data scientists that are putting ML model into production.

Recent studies have shown that slight perturbations in the input data can significantly affect the robustness of Deep Neural Networks (DNNs), leading to misclassification and confidence reduction. In this paper, we introduce a novel technique based on the Selective Sobel Convolution (SSC) operation in the training loop, that increases the robustness of a given DNN by allowing it to learn important edges in the input in a controlled fashion. This is achieved by introducing a trainable parameter, which acts as a threshold for eliminating the weaker edges. We validate our technique against the attacks of Cleverhans library on Convolutional DNNs against adversarial attacks. Our experimental results on the MNIST and CIFAR10 datasets illustrate that this controlled learning considerably increases the accuracy of the DNNs by 1.53% even when subjected to adversarial attacks.

The exponential increase in dependencies between the cyber and physical world leads to an enormous amount of data which must be efficiently processed and stored. Therefore, computing paradigms are evolving towards machine learning (ML)-based systems because of their ability to efficiently and accurately process the enormous amount of data. Although ML-based solutions address the efficient computing requirements of big data, they introduce (new) security vulnerabilities into the systems, which cannot be addressed by traditional monitoring-based security measures. Therefore, this paper first presents a brief overview of various security threats in machine learning, their respective threat models and associated research challenges to develop robust security measures. To illustrate the security vulnerabilities of ML during training, inferencing and hardware implementation, we demonstrate some key security threats on ML using LeNet and VGGNet for MNIST and German Traffic Sign Recognition Benchmarks (GTSRB), respectively. Moreover, based on the security analysis of ML-training, we also propose an attack that has a very less impact on the inference accuracy. Towards the end, we highlight the associated research challenges in developing security measures and provide a brief overview of the techniques used to mitigate such security threats.

Deep neural networks (DNN)-based machine learning (ML) algorithms have recently emerged as the leading ML paradigm particularly for the task of classification due to their superior capability of learning efficiently from large datasets. The discovery of a number of well-known attacks such as dataset poisoning, adversarial examples, and network manipulation (through the addition of malicious nodes) has, however, put the spotlight squarely on the lack of security in DNN-based ML systems. In particular, malicious actors can use these well-known attacks to cause random/targeted misclassification, or cause a change in the prediction confidence, by only slightly but systematically manipulating the environmental parameters, inference data, or the data acquisition block. Most of the prior adversarial attacks have, however, not accounted for the pre-processing noise filters commonly integrated with the ML-inference module. Our contribution in this work is to show that this is a major omission since these noise filters can render ineffective the majority of the existing attacks, which rely essentially on introducing adversarial noise. Apart from this, we also extend the state of the art by proposing a novel pre-processing noise Filter-aware Adversarial ML attack called FAdeML. To demonstrate the effectiveness of the proposed methodology, we generate an adversarial attack image by exploiting the "VGGNet" DNN trained for the "German Traffic Sign Recognition Benchmarks (GTSRB" dataset, which despite having no visual noise, can cause a classifier to misclassify even in the presence of pre-processing noise filters.

Deep Neural Networks (DNNs) have recently been shown vulnerable to adversarial attacks in which the input examples are perturbed to fool these DNNs towards confidence reduction and (targeted or random) misclassification. In this paper, we demonstrate that how an efficient quantization technique can be leveraged to increase the robustness of a given DNN against adversarial attacks. We present two quantization-based defense mechanisms, namely Constant Quantization (CQ) and Variable Quantization (VQ), applied at the input to increase the robustness of DNNs. In CQ, the intensity of the input pixel is quantized according to the number of quantization levels. While in VQ, the quantization levels are recursively updated during the training phase, thereby providing a stronger defense mechanism. We apply our techniques on the Convolutional Neural Networks (CNNs, a particular type of DNN which is heavily used in vision-based applications) against adversarial attacks from the open-source Cleverhans library. Our experimental results show 1%-5% increase in the adversarial accuracy for MNIST and 0%-2.4% increase in the adversarial accuracy for CIFAR10.

When observing the actions of others, humans carry out inferences about why the others acted as they did, and what this implies about their view of the world. Humans also use the fact that their actions will be interpreted in this manner when observed by others, allowing them to act informatively and thereby communicate efficiently with others. Although learning algorithms have recently achieved superhuman performance in a number of two-player, zero-sum games, scalable multi-agent reinforcement learning algorithms that can discover effective strategies and conventions in complex, partially observable settings have proven elusive. We present the Bayesian action decoder (BAD), a new multi-agent learning method that uses an approximate Bayesian update to obtain a public belief that conditions on the actions taken by all agents in the environment. Together with the public belief, this Bayesian update effectively defines a new Markov decision process, the public belief MDP, in which the action space consists of deterministic partial policies, parameterised by deep neural networks, that can be sampled for a given public state. It exploits the fact that an agent acting only on this public belief state can still learn to use its private information if the action space is augmented to be over partial policies mapping private information into environment actions. The Bayesian update is also closely related to the theory of mind reasoning that humans carry out when observing others' actions. We first validate BAD on a proof-of-principle two-step matrix game, where it outperforms traditional policy gradient methods. We then evaluate BAD on the challenging, cooperative partial-information card game Hanabi, where in the two-player setting the method surpasses all previously published learning and hand-coded approaches.

This paper introduces TakeFive, a new semantic role labeling method that transforms a text into a frame-oriented knowledge graph. It performs dependency parsing, identifies the words that evoke lexical frames, locates the roles and fillers for each frame, runs coercion techniques, and formalises the results as a knowledge graph. This formal representation complies with the frame semantics used in Framester, a factual-linguistic linked data resource. The obtained precision, recall and F1 values indicate that TakeFive is competitive with other existing methods such as SEMAFOR, Pikes, PathLSTM and FRED. We finally discuss how to combine TakeFive and FRED, obtaining higher values of precision, recall and F1. Keywords: Semantic Role Labeling, Frame Semantics, Framester, Dependency Parsing, Role Oriented Knowledge Graphs 1. Introduction Most knowledge in linked data and knowledge graphs is of a relational nature: people participating in events, products having prices, artifacts with parts, works of art produced by artists, beers sold at a bar, etc. For that reason, a good part of integration and interoperability ends up consisting in aligning relations among heterogeneous schemas and data. This limit makes interoperability difficult.

Each week I am going to try and remember to post my ML premier league predictor's predictions for the round of fixtures and keep track of how well it is doing in terms of correct results and scores. I will also be including a track of money won and lost if each predicted result was bet on. This will be done using my v2 for now but will transition to v3 when it is complete. I am starting 10 weeks in to the season as most teams have now played 5 home and 5 away games and thus the attributes fed to the machine learning algorithm should be fully populated and give more sensible predictions. Due to the way it is set up in very early weeks attributes like form can behave weirdly if a team has 0 points and another max even if it has only been 1 game.

Abstract: Attention mechanisms have been around since at least 2014, and they have been driving the state of the art in NLP (natural language processing) ever since. Now we are at the end of 2018, and yet it is still very uncommon to hear about their use in enterprise environments. This talk will explain attention mechanisms and how they fit into the deep learning landscape. It will show you the different types of attention mechanisms and examples of them being applied to several different problems. Finally, you will see how you might apply them yourself in models build with Deeplearning4J. Speaker: Paul Dubs (Paul Dubs IT Consulting) Paul holds a Master of Science in Computer Science from TU Darmstadt and has over a decade of professional software engineering experience.

How to invest in big data. In the late 1990s and early 2000s, the internet completely changed the way the business world operates and created a tremendous amount of wealth for investors who picked early winners. The next major technological transition for global businesses will be collection and analysis of data using artificial intelligence. The so-called "big data" revolution will help companies streamline their businesses like never before. But much like the dot-com boom, not all big data stocks will end up winners.