DeepThought: An Architecture for Autonomous Self-motivated Systems

no code implementations • 14 Nov 2023 • Arlindo L. Oliveira, Tiago Domingos, Mário Figueiredo, Pedro U. Lima

We argue that the internal architecture of LLMs and their finite and volatile state cannot support any of these properties.

Single-partition adaptive Q-learning

1 code implementation • 14 Jul 2020 • João Pedro Araújo, Mário Figueiredo, Miguel Ayala Botto

This paper introduces single-partition adaptive Q-learning (SPAQL), an algorithm for model-free episodic reinforcement learning (RL), which adaptively partitions the state-action space of a Markov decision process (MDP), while simultaneously learning a time-invariant policy (i. e., the mapping from states to actions does not depend explicitly on the episode time step) for maximizing the cumulative reward.

Q-Learning Reinforcement Learning (RL)

Restoring STM images via Sparse Coding: noise and artifact removal

no code implementations • 11 Oct 2016 • João P. Oliveira, Ana Bragança, José Bioucas-Dias, Mário Figueiredo, Luís Alcácer, Jorge Morgado, Quirina Ferreira

In this article, we present a denoising algorithm to improve the interpretation and quality of scanning tunneling microscopy (STM) images.

Denoising regression