csAI – Newsemia

Value Driven Representation for Human-in-the-Loop Reinforcement Learning. (arXiv:2004.01223v1 [cs.AI])

NewsemiaApril 6, 2020

by NewsemiaApril 6, 2020030

Interactive adaptive systems powered by Reinforcement Learning (RL) have many potential applications, such as intelligent tutoring systems. In such systems there is typically an external...

AI/ML

Adversarial Stress Testing of Lifetime Distributions. (arXiv:2003.12587v1 [cs.AI])

NewsemiaMarch 31, 2020

by NewsemiaMarch 31, 2020052

In this paper we put forward the viewpoint that the notion of stress testing financial institutions and engineered systems can also be made viable appropos...

AI/ML

Adversarial System Variant Approximation to Quantify Process Model Generalization. (arXiv:2003.12168v1 [cs.AI])

NewsemiaMarch 30, 2020

by NewsemiaMarch 30, 202008

In process mining, process models are extracted from event logs using process discovery algorithms and are commonly assessed using multiple quality dimensions. While the metrics...

AI/ML

Knowledge Graph Alignment using String Edit Distance. (arXiv:2003.12145v1 [cs.AI])

NewsemiaMarch 30, 2020

by NewsemiaMarch 30, 2020022

In this work, we propose a novel knowledge base alignment technique based upon string edit distance that exploits the type information about entities and can...

AI/ML

On Sufficient and Necessary Conditions in Bounded CTL. (arXiv:2003.06492v1 [cs.AI])

NewsemiaMarch 17, 2020

by NewsemiaMarch 17, 2020032

Computation Tree Logic (CTL) is one of the central formalisms in formal verification. As a specification language, it is used to express a property that...

AI/ML

Optimizing Medical Treatment for Sepsis in Intensive Care: from Reinforcement Learning to Pre-Trial Evaluation. (arXiv:2003.06474v1 [cs.AI])

NewsemiaMarch 17, 2020

by NewsemiaMarch 17, 202009

Our aim is to establish a framework where reinforcement learning (RL) of optimizing interventions retrospectively allows us a regulatory compliant pathway to prospective clinical testing...

AI/ML

A Neural Architecture for Detecting Confusion in Eye-tracking Data. (arXiv:2003.06434v1 [cs.AI])

NewsemiaMarch 17, 2020

by NewsemiaMarch 17, 2020038

Encouraged by the success of deep learning in a variety of domains, we investigate a novel application of its methods on the effectiveness of detecting...

AI/ML

On Initializing Airline Crew Pairing Optimization for Large-scale Complex Flight Networks. (arXiv:2003.06423v1 [cs.AI])

NewsemiaMarch 17, 2020

by NewsemiaMarch 17, 2020041

Crew pairing optimization (CPO) is critically important for any airline, since its crew operating costs are second-largest, next to the fuel-cost. CPO aims at generating...

AI/ML

Learning Compositional Rules via Neural Program Synthesis. (arXiv:2003.05562v1 [cs.AI])

NewsemiaMarch 15, 2020

by NewsemiaMarch 15, 2020038

Many aspects of human reasoning, including language, require learning rules from very little data. Humans can do this, often learning systematic rules from very few...

AI/ML

Behavior Cloning in OpenAI using Case Based Reasoning. (arXiv:2002.11197v1 [cs.AI])

NewsemiaFebruary 27, 2020

by NewsemiaFebruary 27, 202003

Learning from Observation (LfO), also known as Behavioral Cloning, is an approach for building software agents by recording the behavior of an expert (human or...

AI/ML

TanksWorld: A Multi-Agent Environment for AI Safety Research. (arXiv:2002.11174v1 [cs.AI])

NewsemiaFebruary 27, 2020

by NewsemiaFebruary 27, 2020040

The ability to create artificial intelligence (AI) capable of performing complex tasks is rapidly outpacing our ability to ensure the safe and assured operation of...

AI/ML

Topologically sensitive metaheuristics. (arXiv:2002.11164v1 [cs.AI])

NewsemiaFebruary 27, 2020

by NewsemiaFebruary 27, 202008

This paper proposes topologically sensitive metaheuristics, and describes conceptual design of topologically sensitive Variable Neighborhood Search method (TVNS) and topologically sensitive Electromagnetism Metaheuristic (TEM). Source...

AI/ML

Very simple statistical evidence that AlphaGo has exceeded human limits in playing GO game. (arXiv:2002.11107v1 [cs.AI])

NewsemiaFebruary 27, 2020

by NewsemiaFebruary 27, 2020035

Deep learning technology is making great progress in solving the challenging problems of artificial intelligence, hence machine learning based on artificial neural networks is in...

AI/ML

A Double Q-Learning Approach for Navigation of Aerial Vehicles with Connectivity Constraint. (arXiv:2002.10563v1 [cs.AI])

NewsemiaFebruary 26, 2020

by NewsemiaFebruary 26, 2020011

This paper studies the trajectory optimization problem for an aerial vehicle with the mission of flying between a pair of given initial and final locations....

AI/ML

Efficient exploration of zero-sum stochastic games. (arXiv:2002.10524v1 [cs.AI])

NewsemiaFebruary 26, 2020

by NewsemiaFebruary 26, 202002

We investigate the increasingly important and common game-solving setting where we do not have an explicit description of the game but only oracle access to...

AI/ML

Neural Lyapunov Model Predictive Control. (arXiv:2002.10451v1 [cs.AI])

NewsemiaFebruary 26, 2020

by NewsemiaFebruary 26, 2020034

This paper presentsNeural Lyapunov MPC, analgorithm to alternately train a Lyapunov neuralnetwork and a stabilising constrained Model Pre-dictive Controller (MPC), given a neural networkmodel of...

AI/ML

The Pragmatic Turn in Explainable Artificial Intelligence (XAI). (arXiv:2002.09595v1 [cs.AI])

NewsemiaFebruary 25, 2020

by NewsemiaFebruary 25, 2020029

In this paper I argue that the search for explainable models and interpretable decisions in AI must be reformulated in terms of the broader project...

AI/ML

A Road Map to Strong Intelligence. (arXiv:2002.09044v1 [cs.AI])

NewsemiaFebruary 24, 2020

by NewsemiaFebruary 24, 202002

I wrote this paper because technology can really improve people’s lives. With it, we can live longer in a healthy body, save time through increased...

AI/ML

A Model-Based, Decision-Theoretic Perspective on Automated Cyber Response. (arXiv:2002.08957v1 [cs.AI])

NewsemiaFebruary 24, 2020

by NewsemiaFebruary 24, 2020065

Cyber-attacks can occur at machine speeds that are far too fast for human-in-the-loop (or sometimes on-the-loop) decision making to be a viable option. Although human...

AI/ML

Tree Search vs Optimization Approaches for Map Generation. (arXiv:1903.11678v2 [cs.AI] UPDATED)

NewsemiaFebruary 23, 2020

by NewsemiaFebruary 23, 2020031

Search-based procedural content generation uses stochastic global optimization algorithms to search spaces of game content. However, it has been found that tree search can be...