IX Simposio Peruano de Inteligencia Artificial (SPIA 2017)
IX Simposio Peruano de Inteligencia Artificial (SPIA 2017)
As is tradition in last years, the IX Peruvian Symposium on Artificial Intelligence SPIA-2017 will be held in Arequipa, organized by the Artificial Intelligence group of the Computer Science Peruvian Society (Sociedad Peruana de Computación - SPC) with the support of Universidad Católica San Pablo (UCSP), Universidad Nacional de San Agustín (UNSA), Universidad La Salle, the IEEE Computational Intelligence Society Peruvian Chapter (IEEE-CIS) and will take place on 2018 January 04th-5th.
SPIA is a forum that is opened for the presentation of current and relevant scientific research in the area of Artificial Intelligence in which, researchers as well as graduate and undergraduate students interested in making science can discuss the advances and achievements obtained in their research projects as well as debate about the possible contributions that can be made in each sub-area of knowledge.
Usually, SPIA includes a program lectures or tutorials that will facilitate academic exchange between the local, national and international scientific community, and will increase the visibility of research conducted both locally, nationally and internationally.
Date and Time
Location
Hosts
Registration
-
Add Event to Calendar
- Universidad Católica San Pablo
- Quinta Vivanco S/N Urb. Campiña Paisajista
- Arequipa, Arequipa
- Peru 04001
- Building: Auditorium San Juan Pablo II
- Room Number: D07
- Click here for Map
- Contact Event Host
- Co-sponsored by Peruvian Computing Society (SPC)
Speakers
Omar Florez of Intel Labs
Learning to Play DOOM
In contrast to supervised learning, there are different problem settings in which we rarely observe labels and most of the information is expressed in terms of rewards and goals. Different instantiations of these type of problems show the need of learning by reinforcing rewards in the environment, just like a video game. In this talk, we will teach an agent to play DOOM with the goal of surviving in an environment with opponents and limited munitions supply.
Address:California, United States
Francisco Cruz
Teaching Robots With Interactive Reinforcement Learning
We investigate learning approaches, more specifically interactive reinforcement learning to perform a domestic task. We use parent-like advice to explore two set-ups: agent-agent and human-agent interaction.
In this presentation, we show our contribution to knowledge in terms of studying the interplay of multi-modal interactive feedback and contextual affordances. Overall, we investigate which parameters influence the interactive reinforcement learning process and show that the apprenticeship of reinforcement learning agents can be sped up by means of interactive parent-like advice, multi-modal feedback, and affordances-driven environmental models.
Address:Region Metropolitana, Chile
Agenda
January 5th, 08:30 - 09:15h
Registrations and Opening
January 5th, 09:15 - 10:00h
Detection of diabetic retinopathy based on a convolutional neural network using retinal fundus images
Manasses Antoni Mauricio Condori (UCSP)
January 5th, 10:00 - 10:45h
Teaching Robots With Interactive Reinforcement Learning
Francisco Cruz (UChile)
January 5th, 10:45 - 11:30h
Extractive document summarization using complex network measurements
Jorge Andoni Valverde Tohalino (USP)
January 5th, 11:30 - 12:15h
Learning to Play DOOM
Omar U. Florez (Intel Labs California)