Addressing fairness in machine learning models has recently attracted a lot of attention, as it will ensure continued confidence of the general public in the deployment of machine learning systems. Here, we focus on mitigating harm of a biased system that offers much better quality outputs for certain groups than for others. We show that bias in the output can naturally be handled in Gaussian process classification (GPC) models by introducing a latent target output that will modulate the likelihood function. This simple formulation has several advantages: first, it is a unified framework for several notions of fairness (demographic parity, equalized odds, and equal opportunity); second, it allows encoding our knowledge of what the bias in outputs should be; and third, it can be solved by using off-the-shelf GPC packages.

At present, the state-of-the-art computational models across a range of sequential data processing tasks, including language modeling, are based on recurrent neural network architectures. This paper begins with the observation that most research on developing computational models capable of processing sequential data fails to explicitly analyze the long distance dependencies (LDDs) within the datasets the models process. In this context, in this paper, we make five research contributions. First, we argue that a key step in modeling sequential data is to understand the characteristics of the LDDs within the data. Second, we present a method to compute and analyze the LDD characteristics of any sequential dataset, and demonstrate this method on a number of sequential datasets that are frequently used for model benchmarking. Third, based on the analysis of the LDD characteristics within the benchmarking datasets, we observe that LDDs are far more complex than previously assumed, and depend on at least four factors: (i) the number of unique symbols in a dataset, (ii) size of the dataset, (iii) the number of interacting symbols within an LDD, and (iv) the distance between the interacting symbols. Fourth, we verify these factors by using synthetic datasets generated using Strictly k-Piecewise (SPk) languages. We then demonstrate how SPk languages can be used to generate benchmarking datasets with varying degrees of LDDs. The advantage of these synthesized datasets being that they enable the targeted testing of recurrent neural architectures. Finally, we demonstrate how understanding the characteristics of the LDDs in a dataset can inform better hyper-parameter selection for current state-of-the-art recurrent neural architectures and also aid in understanding them...

In this Book we argue that the fruitful interaction of computer vision and belief calculus is capable of stimulating significant advances in both fields. From a methodological point of view, novel theoretical results concerning the geometric and algebraic properties of belief functions as mathematical objects are illustrated and discussed in Part II, with a focus on both a perspective 'geometric approach' to uncertainty and an algebraic solution to the issue of conflicting evidence. In Part III we show how these theoretical developments arise from important computer vision problems (such as articulated object tracking, data association and object pose estimation) to which, in turn, the evidential formalism is able to provide interesting new solutions. Finally, some initial steps towards a generalization of the notion of total probability to belief functions are taken, in the perspective of endowing the theory of evidence with a complete battery of estimation and inference tools to the benefit of all scientists and practitioners.

The Information Flow Framework (IFF) [1] is a descriptive category metatheory currently under development, which is being offered as the structural aspect of the Standard Upper Ontology (SUO). The architecture of the IFF is composed of metalevels, namespaces and meta-ontologies. The main application of the IFF is institutional: the notion of institutions and their morphisms are being axiomatized in the upper metalevels of the IFF, and the lower metalevel of the IFF has axiomatized various institutions in which semantic integration has a natural expression as the colimit of theories. Some of the ideas used in this paper first appeared in papers by Joseph Goguen [2] and the author [3], and discussions on the SUO email list. See also the companion paper [4]. Keywords: descriptive category metatheory, institutions, semantic integration "Philosophy cannot become scientifically healthy without an immense technical vocabulary. We can hardly imagine our great-grandsons turning over the leaves of this dictionary without amusement over the paucity of words with which their grandsires attempted to handle metaphysics and logic. Long before that day, it will have become indispensably requisite, too, that each of these terms should be confinedto a single meaning which, however broad, must be free from all vagueness. This will involve a revolution in terminology; for in its present condition a philosophical thought of any precision can seldom be expressed without lengthy explanations."

Nowadays, the success of neural networks as reasoning systems is doubtless. Nonetheless, one of the drawbacks of such reasoning systems is that they work as black-boxes and the acquired knowledge is not human readable. In this paper, we present a new step in order to close the gap between connectionist and logic based reasoning systems. We show that two of the most used inference rules for obtaining negative information in rule based reasoning systems, the so-called Closed World Assumption and Negation as Finite Failure can be characterized by means of spiking neural P systems, a formal model of the third generation of neural networks born in the framework of membrane computing. Keywords: P systems, Neural-symbolic integration, Membrane computing 1. Introduction In the last years, the scientific community has paid more and more attention to artificial neural networks due to the doubtless success of such devices in many real-world problems.

Within a decade, almost every major auto company, along with fleet operators such as Uber, have announced plans to put autonomous vehicles on the road. At the same time, electric vehicles are quickly emerging as a next-generation technology that is cost effective, in addition to offering the benefits of reducing the carbon footprint. The combination of a centrally managed fleet of driverless vehicles, along with the operating characteristics of electric vehicles, is creating a transformative new technology that offers significant cost savings with high service levels. This problem involves a dispatch problem for assigning riders to cars, a planning problem for deciding on the fleet size, and a surge pricing problem for deciding on the price per trip. In this work, we propose to use approximate dynamic programming to develop high-quality operational dispatch strategies to determine which car (given the battery level) is best for a particular trip (considering its length and destination), when a car should be recharged, and when it should be re-positioned to a different zone which offers a higher density of trips. We then discuss surge pricing using an adaptive learning approach to decide on the price for each trip. Finally, we discuss the fleet size problem which depends on the previous two problems.

The efficiency and dynamism of Unmanned Aerial Vehicles (UAVs), or drones, present substantial application opportunities in several industries in the last years. Notably, the logistic companies gave close attention to these vehicles envisioning reduce delivery time and operational cost. A variant of the Traveling Salesman Problem (TSP) called Flying Sidekick Traveling Salesman Problem (FSTSP) was introduced involving drone-assisted parcel delivery. The drone is launched from the truck, proceeds to deliver parcels to a customer and then is recovered by the truck in a third location. While the drone travels through a trip, the truck delivers parcels to other customers as long as the drone has enough battery to hover waiting for the truck. This work proposes a hybrid heuristic that the initial solution is created from the optimal TSP solution reached by a TSP solver. Next, an implementation of the General Variable Neighborhood Search is used to obtain the delivery routes of truck and drone. Computational experiments show the potential of the algorithm to improve the delivery time significantly. Furthermore, we provide a new set of instances based on well-known TSPLIB instances.

An Austrian computer repairman has amassed what he believes could be the world's biggest collection of old Apple computers, but it might all soon be destroyed unless someone can take it off his hands. Over the years since he began working for a company that repaired Apples in Vienna in the 1980s, Roland Borsky's collection has grown to roughly 1,100 computers, he says - far more than the 472 items at Prague's Apple Museum, which says it is the world's biggest private collection of Apple products. 'Just as others collect cars and live in a little box to afford them, so it is with me,' he said in his office, which is so packed with dusty items like a wall of old monitors that he has moved most of them to a warehouse outside the city. Austrian Apple computer collector Roland Borsky makes a phone call in his office in Vienna, Austria September 28, 2018. Ironically, however, Apple's success has made life harder for his business, and he has decided to close it.

If you've spent much time on Nanalyze, you know that we're passionate about technology and believe that we're living in the most exciting times in history. Our job is to keep you up-to-date about these changes in a variety of fields, so you can make informed financial decisions about where to invest or not--and learn some pretty cool stuff along the way. We talk about the good, the bad and ugly no matter what. Then we came across Narrative Science and its natural language generation (NLG) platform Quill, which uses artificial intelligence technology to write everything from financial reports to sports news. We knew that English degree would be obsolete someday.

If you happened to be in Milan on October 11 or 12 you would have felt the atmosphere of the fashionable future thanks to PI Apparel 2018 – the most innovative gathering of the fashion industry. Several times a year, in different locations, this trade fair brings together top brands, consultants and most progressive fashion startups, to discuss challenges and share experience on digital product creation, augmented and virtual reality AI, machine learning, automation & robotics and many more. Taking part in this event, I was given the opportunity to meet incredible people and explore strategies and ideas from the most advanced companies. Having met and spoken to various companies at the event, here is a list of the startups to watch, if you want to keep up with front-rank technologies in the apparel industry. Founded in 2017, Swatchbook creates cross-platform cloud software that changes the way brands work with materials.