Arrow Research search

Author name cluster

Michael Anderson

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

8 papers
1 author row

Possible papers

8

AAAI Conference 2014 Conference Paper

GenEth: A General Ethical Dilemma Analyzer

  • Michael Anderson
  • Susan Anderson

We contend that ethically significant behavior of autonomous systems should be guided by explicit ethical principles determined through a consensus of ethicists. To provide assistance in developing these ethical principles, we have developed GENETH, a general ethical dilemma analyzer that, through a dialog with ethicists, codifies ethical principles in any given domain. GENETH has been used to codify principles in a number of domains pertinent to the behavior of autonomous systems and these principles have been verified using an Ethical Turing Test.

PDF Details

NeurIPS Conference 2013 Conference Paper

Adaptive Multi-Column Deep Neural Networks with Application to Robust Image Denoising

  • Forest Agostinelli
  • Michael Anderson
  • Honglak Lee

Stacked sparse denoising auto-encoders (SSDAs) have recently been shown to be successful at removing noise from corrupted images. However, like most denoising techniques, the SSDA is not robust to variation in noise types beyond what it has seen during training. We present the multi-column stacked sparse denoising autoencoder, a novel technique of combining multiple SSDAs into a multi-column SSDA (MC-SSDA) by combining the outputs of each SSDA. We eliminate the need to determine the type of noise, let alone its statistics, at test time. We show that good denoising performance can be achieved with a single system on a variety of different noise types, including ones not seen in the training set. Additionally, we experimentally demonstrate the efficacy of MC-SSDA denoising by achieving MNIST digit error rates on denoised images at close to that of the uncorrupted images.

PDF Details

AAAI Conference 1999 Conference Paper

Towards Diagram Processing: A Diagrammatic Information System

  • Michael Anderson
  • University of Hartford

We advocate the development of an agent capable of processing diagrammatic information directly in all its forms. In the same way that we will require intelligent agents to be conversant with natural language, we will expect them to be fluent with diagrammatic information and its processing. We present a methodology to this end, detail a diagrammatic information system that shows the merit of this line of research, and evaluate this system to motivate its future extensions.

PDF Details

AAAI Conference 1996 Conference Paper

Diagrammatic Reasoning and Cases

  • Michael Anderson

We believe that many problem domains that lend themselves to a case-based reasoning solution can benefit from an diagrammatic implementation and propose a diagrammatic case-based solution to what we term the n-queens best solution problem where the best solution is defined as that which solves the probfem moving the fewest queens. A working system, based on a novel combination of diagrammatic and case-based reasoning, is described. the problem in the fewest moves). Further, we develop an inter-diagrammatic implementation of the min-conflicts heuristic [Gu 1989-J to find solutions to randomly chosen n-queens problems [Stone & Stone 19861 themselves.

PDF Details

IJCAI Conference 1995 Conference Paper

Inter-diagrammatic Reasoning

  • Michael Anderson
  • Robert McCartney

Endowing a computer with an ability to reason with diagrams could be of great benefit in terms of both human-computer interaction and computational efficiency through explicit representation. To date, research in diagrammatic reasoning has dealt with intra-diagrammatic reasoning (reasoning with a single diagram) almost to the exclusion of inter-diagrammatic reasoning (reasoning with related groups of diagrams). We postulate a number of general inter-diagrammatic operators and show how such operators can be useful in various diagrammatic domains. We develop a heuristic in the domain of game notation, derive fingering information in the domain of musical notation, and infer new information from related cartograms.

PDF