Banca de DEFESA: ANDRE OLIVEIRA MACEDO

Uma banca de DEFESA de MESTRADO foi cadastrada pelo programa.
STUDENT : ANDRE OLIVEIRA MACEDO
DATE: 21/11/2023
TIME: 14:00
LOCAL: Virtual
TITLE:

Neural models in virtual environments

PAGES: 120
BIG AREA: Outra
AREA: Multidisciplinar
SUMMARY:

This project investigates neural network modeling by juxtaposing different neural networks in the context of behavior modeling and reinforcement learning. Taking advantage of several neural architectures, including densely connected, recurrent (RNN) and convolutional networks (CNN), their parameters and performances are analyzed within the "snake game". The experiments point to greater computational consumption, greater difficulty in adjusting parameters, but greater stability in some metrics of the more biologically detailed models, such as spike networks and liquid state machines, revealing a contrasting dynamic with the training of better known neural networks such as RNN and CNN. In comparison, these models performed satisfactorily in the tasks, obtaining high scores and producing balanced strategies of conservative and exploitative behaviors. It was concluded that the comparative analysis deepens the way of verifying and understanding the training of neural networks, complementing the analyzes of metrics carried out for the evaluation of artificial neural networks, such as the total loss or entropy.

COMMITTEE MEMBERS:
Presidente - Interno ao Programa - 2134537 - FABIO MARQUES SIMOES DE SOUZA
Membro Titular - Examinador(a) Interno ao Programa - 1672981 - FRANCISCO JAVIER ROPERO PELAEZ
Membro Titular - Examinador(a) Externo à Instituição - ANTÔNIO CARLOS ROQUE DA SILVA FILHO - USP
Membro Suplente - Examinador(a) Interno ao Programa - 1676329 - RAPHAEL YOKOINGAWA DE CAMARGO
Membro Suplente - Examinador(a) Interno ao Programa - 1722875 - DAVID CORREA MARTINS JUNIOR
Membro Suplente - Examinador(a) Externo à Instituição - OSAME KINOUCHI