<?xml version="1.0" encoding="UTF-8"?><xml><records><record><source-app name="Biblio" version="7.x">Drupal-Biblio</source-app><ref-type>47</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Parussel, Karla</style></author><author><style face="normal" font="default" size="100%">Lola Cañamero</style></author></authors><secondary-authors><author><style face="normal" font="default" size="100%">de Sá, Joaquim Marques</style></author><author><style face="normal" font="default" size="100%">Alexandre, Luís A.</style></author><author><style face="normal" font="default" size="100%">Duch, Włodzisław</style></author><author><style face="normal" font="default" size="100%">Mandic, Danilo</style></author></secondary-authors></contributors><titles><title><style face="normal" font="default" size="100%">Biasing Neural Networks Towards Exploration or Exploitation Using Neuromodulation</style></title><secondary-title><style face="normal" font="default" size="100%">Proc. 17th International Conference on Artificial Neural Networks (ICANN 2007), Part II</style></secondary-title><tertiary-title><style face="normal" font="default" size="100%">LNCS</style></tertiary-title></titles><dates><year><style  face="normal" font="default" size="100%">2007</style></year><pub-dates><date><style  face="normal" font="default" size="100%">09/2007</style></date></pub-dates></dates><urls><web-urls><url><style face="normal" font="default" size="100%">https://link.springer.com/chapter/10.1007/978-3-540-74695-9_91</style></url></web-urls></urls><publisher><style face="normal" font="default" size="100%">Springer Berlin Heidelberg</style></publisher><pub-location><style face="normal" font="default" size="100%">Porto, Portugal</style></pub-location><volume><style face="normal" font="default" size="100%">4669</style></volume><pages><style face="normal" font="default" size="100%">889–898</style></pages><isbn><style face="normal" font="default" size="100%">978-3-540-74695-9</style></isbn><language><style face="normal" font="default" size="100%">eng</style></language><abstract><style face="normal" font="default" size="100%">Taking neuromodulation as a mechanism underlying emotions, this paper investigates how such a mechanism can bias an artificial neural network towards exploration of new courses of action, as seems to be the case in positive emotions, or exploitation of known possibilities, as in negative emotions such as predatory fear. We use neural networks of spiking leaky integrate-and-fire neurons acting as minimal disturbance systems, and test them with continuous actions. The networks have to balance the activations of all their output neurons concurrently. We have found that having the middle layer modulate the output layer helps balance the activations of the output neurons. A second discovery is that when the network is modulated in this way, it performs better at tasks requiring the exploitation of actions that are found to be rewarding. This is complementary to previous findings where having the input layer modulate the middle layer biases the network towards exploration of alternative actions. We conclude that a network can be biased towards either exploration of exploitation depending on which layers are being modulated.</style></abstract></record><record><source-app name="Biblio" version="7.x">Drupal-Biblio</source-app><ref-type>47</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Lola Cañamero</style></author><author><style face="normal" font="default" size="100%">Avila-García, Orlando</style></author></authors><secondary-authors><author><style face="normal" font="default" size="100%">Ana C R Paiva</style></author><author><style face="normal" font="default" size="100%">Rui Prada</style></author><author><style face="normal" font="default" size="100%">Rosalind W Picard</style></author></secondary-authors></contributors><titles><title><style face="normal" font="default" size="100%">A Bottom-Up Investigation of Emotional Modulation in Competitive Scenarios</style></title><secondary-title><style face="normal" font="default" size="100%">Proc. Second International Conference on Affective Computing and Intelligent Interaction (ACII 2007)</style></secondary-title><tertiary-title><style face="normal" font="default" size="100%">Lecture Notes in Computer Science</style></tertiary-title></titles><dates><year><style  face="normal" font="default" size="100%">2007</style></year><pub-dates><date><style  face="normal" font="default" size="100%">09/2007</style></date></pub-dates></dates><publisher><style face="normal" font="default" size="100%">Springer Berlin Heidelberg</style></publisher><pub-location><style face="normal" font="default" size="100%">Lisbon, Portugal</style></pub-location><volume><style face="normal" font="default" size="100%">4738</style></volume><pages><style face="normal" font="default" size="100%">398–409</style></pages><isbn><style face="normal" font="default" size="100%">978-3-540-74888-5</style></isbn><language><style face="normal" font="default" size="100%">eng</style></language><abstract><style face="normal" font="default" size="100%">In this paper, we take an incremental, bottom-up approach to investigate plausible mechanisms underlying emotional modulation of behavior selection and their adaptive value in autonomous robots. We focus in particular on achieving adaptive behavior selection in competitive robotic scenarios through modulation of perception, drawing on the notion of biological hormones. We discuss results from testing our architectures in two different competitive robotic scenarios.</style></abstract></record><record><source-app name="Biblio" version="7.x">Drupal-Biblio</source-app><ref-type>47</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Cañamero, Lola D</style></author></authors><secondary-authors><author><style face="normal" font="default" size="100%">Cañamero, Lola D</style></author></secondary-authors></contributors><titles><title><style face="normal" font="default" size="100%">Building Emotional Artifacts in Social Worlds: Challenges and Perspectives</style></title><secondary-title><style face="normal" font="default" size="100%">Emotional and Intelligent II: The Tangled Knot of Social Cognition; Papers from the 2001 AAAI Fall Symposium</style></secondary-title></titles><dates><year><style  face="normal" font="default" size="100%">2001</style></year></dates><publisher><style face="normal" font="default" size="100%">AAAI Press</style></publisher><pub-location><style face="normal" font="default" size="100%">North Falmouth, Massachusetts</style></pub-location><pages><style face="normal" font="default" size="100%">22–30</style></pages><isbn><style face="normal" font="default" size="100%">978-1-57735-136-8</style></isbn><language><style face="normal" font="default" size="100%">eng</style></language><abstract><style face="normal" font="default" size="100%">This paper discusses ideas relative to the construction of emotional artifacts that have to interact in a social world, and in particular with humans. It first examines some of the ways in which emotions can enhance social interactions with artifacts, and some of the challenges posed to the designer. After considering the debate that opposes &quot;shallow&quot; versus &quot;deep&quot; modeling, it sketches some ways in which we can anchor emotions in the architecture of artifacts in order to make emotional interactions meaningful not only to the human, but also to the artifact itself. It finally outlines some of the cognitive capabilities that artifacts should incorporate for their emotions to be properly grounded and to give rise to rich social exchanges with humans.</style></abstract></record></records></xml>