Goto

Collaborating Authors

logic


Call of Duty's merged world has everything a player could want. Except logic.

Washington Post - Technology News

After the merger and the launch of "Call of Duty: Black Ops Cold War" Season One, there's ample evidence either this plan hadn't been properly conceived, or that the technical barriers to merging these games were too big to fully overcome. Instead of syncing the three games in any intelligent fashion, everything just feels lumped together. The user interface is complicated and messy, largely due to the sheer volume of stuff being forced to coexist in the same place. Transitioning multiplayer parties to or from "Cold War" to one of the other games usually results in dropped players. Similar components, like finishing moves, are equipped differently in "Cold War" than they are in "Warzone" or "Modern Warfare."


Neurosymbolic AI: The 3rd Wave

arXiv.org Artificial Intelligence

Current advances in Artificial Intelligence (AI) and Machine Learning (ML) have achieved unprecedented impact across research communities and industry. Nevertheless, concerns about trust, safety, interpretability and accountability of AI were raised by influential thinkers. Many have identified the need for well-founded knowledge representation and reasoning to be integrated with deep learning and for sound explainability. Neural-symbolic computing has been an active area of research for many years seeking to bring together robust learning in neural networks with reasoning and explainability via symbolic representations for network models. In this paper, we relate recent and early research results in neurosymbolic AI with the objective of identifying the key ingredients of the next wave of AI systems. We focus on research that integrates in a principled way neural network-based learning with symbolic knowledge representation and logical reasoning. The insights provided by 20 years of neural-symbolic computing are shown to shed new light onto the increasingly prominent role of trust, safety, interpretability and accountability of AI. We also identify promising directions and challenges for the next decade of AI research from the perspective of neural-symbolic systems.


Epistemic Logic of Know-Who

arXiv.org Artificial Intelligence

The paper suggests a definition of "know who" as a modality using Grove-Halpern semantics of names. It also introduces a logical system that describes the interplay between modalities "knows who", "knows", and "for all agents". The main technical result is a completeness theorem for the proposed system.


Opening the 'black box' of artificial intelligence

#artificialintelligence

Artificial intelligence is growing ever more powerful and entering people's daily lives, yet often we don't know what goes on inside these systems. Their non-transparency could fuel practical problems, or even racism, which is why researchers increasingly want to open this'black box' and make AI explainable. When decisions are made by artificial intelligence, it can be difficult for the end user to understand the reasoning behind them. In February of 2013, Eric Loomis was driving around in the small town of La Crosse in Wisconsin, US, when he was stopped by the police. The car he was driving turned out to have been involved in a shooting, and he was arrested.


Getting AI to Reason: Using Neuro-Symbolic AI for Knowledge-Based Question Answering

#artificialintelligence

Language is what makes us human. Asking questions is how we learn. Building on the foundations of deep learning and symbolic AI, we have developed technology that can answer complex questions with minimal domain-specific training. Initial results are very encouraging – the system outperforms current state-of-the-art techniques on two prominent datasets with no need for specialized end-to-end training. As this technology matures, it will be possible to use it for better customer support, business intelligence, medical informatics, advanced discovery, and much more.


MLOps [1] - What is Machine Learning?

#artificialintelligence

This video and post are part of a One Dev Question series on MLOps - DevOps for Machine Learning. See the full video playlist here, and the rest of the blog posts here. To understand what MLOps (DevOps for Machine Learning) is, we first need to know what Machine Learning is. Machine Learning is a term many of us have heard, but what does it actually mean, and when should it be used? As usual Microsoft Docs has some great resources, including an explanation of what machine learning is and how it works, but I like to think of it in more simple terms.


Opening the 'black box' of artificial intelligence

#artificialintelligence

Artificial intelligence is growing ever more powerful and entering people's daily lives, yet often we don't know what goes on inside these systems. Their non-transparency could fuel practical problems, or even racism, which is why researchers increasingly want to open this'black box' and make AI explainable. In February of 2013, Eric Loomis was driving around in the small town of La Crosse in Wisconsin, US, when he was stopped by the police. The car he was driving turned out to have been involved in a shooting, and he was arrested. Eventually a court sentenced him to six years in prison.


Opening the 'Black Box' of Artificial Intelligence

#artificialintelligence

In February of 2013, Eric Loomis was driving around in the small town of La Crosse in Wisconsin, US, when he was stopped by the police. The car he was driving turned out to have been involved in a shooting, and he was arrested. Eventually a court sentenced him to six years in prison. This might have been an uneventful case, had it not been for a piece of technology that had aided the judge in making the decision. They used COMPAS, an algorithm that determines the risk of a defendant becoming a recidivist.


Yellowmessenger Chatbot Developer

#artificialintelligence

Are you a programmer who wants to understand how to customize Conversational Chat bots programmatically on the YM platform? In this course, you will learn the core Programming concepts of YM Platform known as Cloud Functions in order to customize your Chat bot. You will write custom logic using Cloud Function – Objects and methods, and test that logic using the built-in testing tool. You will explore how Cloud Functions interacts with UI of the platform. You will get hands-on experience writing code to customize your chat bot interface to support different channels, as well as a brief introduction to the built in Database.


Paraconsistent Intelligent-Based Systems - Programmer Books

#artificialintelligence

This book presents some of the latest applications of new theories based on the concept of paraconsistency and correlated topics in informatics, such as pattern recognition (bioinformatics), robotics, decision-making themes, and sample size. Each chapter is self-contained, and an introductory chapter covering the logic theoretical basis is also included. The aim of the text is twofold: to serve as an introductory text on the theories and applications of new logic, and as a textbook for undergraduate or graduate-level courses in AI. Today AI frequently has to cope with problems of vagueness, incomplete and conflicting (inconsistent) information. One of the most notable formal theories for addressing them is paraconsistent (paracomplete and non-alethic) logic.