Question Answering (QA), as a research field, has primarily focused on either knowledge bases (KBs) or free text as a source of knowledge. These two sources have historically shaped the kinds of questions that are asked over these sources, and the methods developed to answer them. In this work, we look towards a practical use-case of QA over user-instructed knowledge that uniquely combines elements of both structured QA over knowledge bases, and unstructured QA over narrative, introducing the task of multi-relational QA over personal narrative. As a first step towards this goal, we make three key contributions: (i) we generate and release TextWorldsQA, a set of five diverse datasets, where each dataset contains dynamic narrative that describes entities and relations in a simulated world, paired with variably compositional questions over that knowledge, (ii) we perform a thorough evaluation and analysis of several state-of-the-art QA models and their variants at this task, and (iii) we release a lightweight Python-based framework we call TextWorlds for easily generating arbitrary additional worlds and narrative, with the goal of allowing the community to create and share a growing collection of diverse worlds as a test-bed for this task.

Effective network slicing requires an infrastructure/network provider to deal with the uncertain demand and real-time dynamics of network resource requests. Another challenge is the combinatorial optimization of numerous resources, e.g., radio, computing, and storage. This article develops an optimal and fast real-time resource slicing framework that maximizes the long-term return of the network provider while taking into account the uncertainty of resource demand from tenants. Specifically, we first propose a novel system model which enables the network provider to effectively slice various types of resources to different classes of users under separate virtual slices. We then capture the real-time arrival of slice requests by a semi-Markov decision process. To obtain the optimal resource allocation policy under the dynamics of slicing requests, e.g., uncertain service time and resource demands, a Q-learning algorithm is often adopted in the literature. However, such an algorithm is notorious for its slow convergence, especially for problems with large state/action spaces. This makes Q-learning practically inapplicable to our case in which multiple resources are simultaneously optimized. To tackle it, we propose a novel network slicing approach with an advanced deep learning architecture, called deep dueling that attains the optimal average reward much faster than the conventional Q-learning algorithm. This property is especially desirable to cope with real-time resource requests and the dynamic demands of users. Extensive simulations show that the proposed framework yields up to 40% higher long-term average return while being few thousand times faster, compared with state of the art network slicing approaches.

Of primary importance in formulating a response to the increasing prevalence and power of artificial intelligence (AI) applications in society are questions of ontology. Questions such as: What "are" these systems? How are they to be regarded? How does an algorithm come to be regarded as an agent? We discuss three factors which hinder discussion and obscure attempts to form a clear ontology of AI: (1) the various and evolving definitions of AI, (2) the tendency for pre-existing technologies to be assimilated and regarded as "normal," and (3) the tendency of human beings to anthropomorphize. This list is not intended as exhaustive, nor is it seen to preclude entirely a clear ontology, however, these challenges are a necessary set of topics for consideration. Each of these factors is seen to present a 'moving target' for discussion, which poses a challenge for both technical specialists and non-practitioners of AI systems development (e.g., philosophers and theologians) to speak meaningfully given that the corpus of AI structures and capabilities evolves at a rapid pace. Finally, we present avenues for moving forward, including opportunities for collaborative synthesis for scholars in philosophy and science.

"While there have been advances in artificial intelligence (AI) this year, it's poised to skyrocket in 2019.." So a dozen articles a week begin. But what does this mean to me? I basically understand that "General AI" or computers that can comprehend a wide range of topics and interests, just like people do, is still a long way off However, Machine Learning is here right now. Teaching a model with real-world data and then predicting events using statistics is viable. I don't pretend to understand the ins and outs of the complex mathematics that underpin machine learning.

Deep learning neural networks are relatively straightforward to define and train given the wide adoption of open source libraries. Nevertheless, neural networks remain challenging to configure and train. In his 2012 paper titled "Practical Recommendations for Gradient-Based Training of Deep Architectures" published as a preprint and a chapter of the popular 2012 book "Neural Networks: Tricks of the Trade," Yoshua Bengio, one of the fathers of the field of deep learning, provides practical recommendations for configuring and tuning neural network models. In this post, you will step through this long and interesting paper and pick out the most relevant tips and tricks for modern deep learning practitioners. Practical Recommendations for Deep Learning Neural Network Practitioners Photo by Susanne Nilsson, some rights reserved.

Recently, I did the micro course Machine Learning Explainability on kaggle.com. I can highly recommend this course as I have learned a lot of useful methods to analyse a trained ML model. For a brief overview of the topics covered, this blog post will summarize my learnings. The following paragraphs will explain the methods Permutation Importance, Partial Dependence Plots and SHAP Values. I will illustrate the methods using the famous Titanic dataset.

TLDR; This series is based on the work detecting complex policies in the following real life code story. Code for the series can be found here. In the previous tutorials we outlined our policy classification challenge and showed how we can approach it using the Custom Vision Cognitive Service. This tutorial introduces deep transfer learning as a means to leverage multiple data sources to overcome data scarcity problem. Before we try to build a classifier for our complex policy let's first look at the MNIST dataset to better understand key image classification concepts such as One Hot Encoding, Linear Modeling, Multi Layer Perception, Masking and Convolutions then we will put these concepts together and apply them to our own dataset.

In this latest Data Science Central podcast, we will continue to explore the hot topic of AI and Deep Learning at SAS. We will discuss how the SAS platform enables the development of AI applications and how SAS customers are using this exciting technology today.

In this latest Data Science Central podcast, we will introduce you to the hot topic of AI and Deep Learning at SAS. We will cover what is AI, what capabilities SAS offers, and how data scientists can leverage these deep learning capabilities.

The technology is changing the world rapidly. Employees are frequently worried about their jobs will be taken by AI and other kinds of advanced technology. It is actually happening, just you don't realise it yet! The demand for certain traditional and manual jobs will decline. Instead, new skills will be required to suit the new workplace environment.