Search Results for author: Roman V. Yampolskiy

Found 24 papers, 0 papers with code

Impossibility Results in AI: A Survey

no code implementations1 Sep 2021 Mario Brcic, Roman V. Yampolskiy

An impossibility theorem demonstrates that a particular problem or set of problems cannot be solved as described in the claim.

Decision Making

Death in Genetic Algorithms

no code implementations15 Jul 2021 Micah Burkhardt, Roman V. Yampolskiy

Death has long been overlooked in evolutionary algorithms.

AI Risk Skepticism

no code implementations2 May 2021 Roman V. Yampolskiy

In this work, we survey skepticism regarding AI risk and show parallels with other types of scientific skepticism.

Understanding and Avoiding AI Failures: A Practical Guide

no code implementations22 Apr 2021 Robert M. Williams, Roman V. Yampolskiy

As AI technologies increase in capability and ubiquity, AI accidents are becoming more common.

On Controllability of AI

no code implementations19 Jul 2020 Roman V. Yampolskiy

Invention of artificial general intelligence is predicted to cause a shift in the trajectory of human civilization.

Human $\neq$ AGI

no code implementations11 Jul 2020 Roman V. Yampolskiy

Terms Artificial General Intelligence (AGI) and Human-Level Artificial Intelligence (HLAI) have been used interchangeably to refer to the Holy Grail of Artificial Intelligence (AI) research, creation of a machine capable of achieving goals in a wide range of environments.

Unpredictability of AI

no code implementations29 May 2019 Roman V. Yampolskiy

The young field of AI Safety is still in the process of identifying its challenges and limitations.

Personal Universes: A Solution to the Multi-Agent Value Alignment Problem

no code implementations1 Jan 2019 Roman V. Yampolskiy

AI Safety researchers attempting to align values of highly capable intelligent systems with those of humanity face a number of challenges including personal value extraction, multi-agent value merger and finally in-silico encoding.

Emergence of Addictive Behaviors in Reinforcement Learning Agents

no code implementations14 Nov 2018 Vahid Behzadan, Roman V. Yampolskiy, Arslan Munir

This paper presents a novel approach to the technical analysis of wireheading in intelligent agents.

Q-Learning

Why We Do Not Evolve Software? Analysis of Evolutionary Algorithms

no code implementations12 Oct 2018 Roman V. Yampolskiy

In this paper, we review the state-of-the-art results in evolutionary computation and observe that we do not evolve non trivial software from scratch and with no human intervention.

Human Indignity: From Legal AI Personhood to Selfish Memes

no code implementations2 Oct 2018 Roman V. Yampolskiy

It is possible to rely on current corporate law to grant legal personhood to Artificially Intelligent (AI) agents.

Optical Illusions Images Dataset

no code implementations30 Sep 2018 Robert Max Williams, Roman V. Yampolskiy

Human vision is capable of performing many tasks not optimized for in its long evolution.

Building Safer AGI by introducing Artificial Stupidity

no code implementations11 Aug 2018 Michaël Trazzi, Roman V. Yampolskiy

Artificial Intelligence (AI) achieved super-human performance in a broad variety of domains.

A Psychopathological Approach to Safety Engineering in AI and AGI

no code implementations23 May 2018 Vahid Behzadan, Arslan Munir, Roman V. Yampolskiy

The complexity of dynamics in AI techniques is already approaching that of complex adaptive systems, thus curtailing the feasibility of formal controllability and reachability analysis in the context of AI safety.

Detecting Qualia in Natural and Artificial Agents

no code implementations11 Dec 2017 Roman V. Yampolskiy

The Hard Problem of consciousness has been dismissed as an illusion.

Guidelines for Artificial Intelligence Containment

no code implementations24 Jul 2017 James Babcock, Janos Kramar, Roman V. Yampolskiy

With almost daily improvements in capabilities of artificial intelligence it is more important than ever to develop safety software for use by the AI research community.

The Singularity May Be Near

no code implementations31 May 2017 Roman V. Yampolskiy

Toby Walsh in 'The Singularity May Never Be Near' gives six arguments to support his point of view that technological singularity may happen but that it is unlikely.

Artificial Intelligence Safety and Cybersecurity: a Timeline of AI Failures

no code implementations25 Oct 2016 Roman V. Yampolskiy, M. S. Spellchecker

We suggest that both the frequency and the seriousness of future AI failures will steadily increase.

Verifier Theory and Unverifiability

no code implementations1 Sep 2016 Roman V. Yampolskiy

Despite significant developments in Proof Theory, surprisingly little attention has been devoted to the concept of proof verifier.

Automated Theorem Proving General Classification

Unethical Research: How to Create a Malevolent Artificial Intelligence

no code implementations10 May 2016 Federico Pistono, Roman V. Yampolskiy

Cybersecurity research involves publishing papers about malicious exploits as much as publishing information on how to design tools to protect cyber-infrastructure.

Taxonomy of Pathways to Dangerous AI

no code implementations10 Nov 2015 Roman V. Yampolskiy

In order to properly handle a dangerous Artificially Intelligent (AI) system it is important to understand how the system came to be in such a state.

From Seed AI to Technological Singularity via Recursively Self-Improving Software

no code implementations23 Feb 2015 Roman V. Yampolskiy

Software capable of improving itself has been a dream of computer scientists since the inception of the field.

The Universe of Minds

no code implementations1 Oct 2014 Roman V. Yampolskiy

The paper attempts to describe the space of possible mind designs by first equating all minds to software.

Cannot find the paper you are looking for? You can Submit a new open access paper.