Artificial Intelligence

Schank, Roger C.; Towle, Brendon

doi:10.1017/cbo9780511807947.016

Cited by 6 publications

(3 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…1. See Glassman and Wimsatt (1984); Rasmussen (1987); Schank andWimsatt (1988, 1998); Wimsatt and Schank (1989); Wimsatt (1981Wimsatt ( : 178-181, 1986Wimsatt ( , 1999aWimsatt ( , 1999band Callebaut (1993: 331-334, 378-382, 385-386, 425-427).…”

Section: Notesmentioning

confidence: 99%

An Evolutionary Theory of Resource Distribution (Part 1)

Fix

2019

Preprint

View full text Add to dashboard Cite

The biologist Theodosius Dobzhansky famously wrote that “nothing in biology makes sense except in the light of evolution”. I propose a corollary in economics: <i> nothing in economics makes sense except in the light of human social evolution. </i> [1] I explore here how the evolution of human sociality can help us understand how we distribute resources. Although economists like to deny it, humans are social animals.

show abstract

Section: Notesmentioning

confidence: 99%

An Evolutionary Theory of Resource Distribution (Part 1)

Fix

2019

Preprint

View full text Add to dashboard Cite

show abstract

“…It is now generally agreed that Artificial Intelligence (AI) refers to an interdisciplinary field -encompassing biology, computer science, philosophy, mathematics, engineering and robotics, and cognitive science -concerned with simulating human intelligence using computer-based technologies. This is accomplished by teaching machines how to execute activities that ordinarily require human intelligence, such as visual perception, speech recognition, decision-making, and language translation (Wang and Barabási, 2021;Goel and Davies, 2011;Schank and Towle, 2000;de la Higuera, 2010).…”

Section: Introductionmentioning

confidence: 99%

Enhancing deep learning algorithm accuracy and stability using multicriteria optimization: an application to distributed learning with MNIST digits

et al. 2022

View full text Add to dashboard Cite

The training phase is the most crucial stage during the machine learning process. In the case of labeled data and supervised learning, machine learning entails minimizing the loss function under various constraints. We provide an innovative model for learning with numerous data sets, resulting from the application of multicriteria optimization techniques to existing deep learning algorithms. Data fitting is formulated as a multicriteria model in which each criterion measures the data fitting error on a specific data set. This is an optimization model involving a vector-valued function, and it has to be analyzed using the notion of Pareto efficiency. We present stability results for efficient solutions in the presence of input and output data perturbations. The multiple data set environment comes into play

show abstract

“…It is now accepted that with the term Artificial Intelligence (AI) we identify an interdisciplinary area -which includes biology, computer science, philosophy, mathematics, engineering and robotics, and cognitive sciencefocusing on the simulation of human intelligence by means of computerbased machines. This is done by training machines that are able to perform tasks normally requiring human intelligence, such as visual perception, speech recognition, decision-making, and translation between languages Wang and Barabási (2021); Goel and Davies (2011); Schank and Towle (2000); de la Higuera (2010).…”

Section: Introductionmentioning

confidence: 99%

Mixing Deep Learning and Multiple Criteria Optimization: An Application to Distributed Learning with Multiple Datasets

Torre¹,

Liuzzi²,

Repetto³

et al. 2021

Preprint

View full text Add to dashboard Cite

The training phase is the most important stage during the machine learning process. In the case of labeled data and supervised learning, machine training consists in minimizing the loss function subject to different constraints.In an abstract setting, it can be formulated as a multiple criteria optimization model in which each criterion measures the distance between the output associated with a specific input and its label. Therefore, the fitting term is a vector function and its minimization is intended in the Pareto sense. We provide stability results of the efficient solutions with respect to perturbations of input and output data. We then extend the same approach to the case of learning with multiple datasets. The multiple dataset environment is relevant when reducing the bias due to the choice of a specific training set. We propose a scalarization approach to implement this model and

show abstract

Artificial Intelligence

Abstract: We present a model of behavior that unifies behavior-based acting and conversational policies for speaking. This model is applied to the domain of air traffic control.

Cited by 6 publications

References 0 publications

An Evolutionary Theory of Resource Distribution (Part 1)

An Evolutionary Theory of Resource Distribution (Part 1)

Enhancing deep learning algorithm accuracy and stability using multicriteria optimization: an application to distributed learning with MNIST digits

Mixing Deep Learning and Multiple Criteria Optimization: An Application to Distributed Learning with Multiple Datasets

Contact Info

Product

Resources

About