activity
20122022
most citedTree Search and Quantum Computation

10 citations · 31 across the 12 of their papers we have counts for

collaborators

14 papers

cs.LG2022

The smooth output assumption, and why deep networks are better than wide ones

Luis Sa-Couto, Jose Miguel Ramos, Andreas Wichert

When several models have similar training scores, classical model selection heuristics follow Occam's razor and advise choosing the ones with least capacity. Yet, modern practice w…

cs.LG2022

Understanding the double descent curve in Machine Learning

Luis Sa-Couto, Jose Miguel Ramos, Miguel Almeida +1

The theory of bias-variance used to serve as a guide for model selection when applying Machine Learning algorithms. However, modern practice has shown success with over-parameteriz…

cs.LG2022

Multi-level Data Representation For Training Deep Helmholtz Machines

Jose Miguel Ramos, Luis Sa-Couto, Andreas Wichert

A vast majority of the current research in the field of Machine Learning is done using algorithms with strong arguments pointing to their biological implausibility such as Backprop…

cs.CV2021

Using brain inspired principles to unsupervisedly learn good representations for visual pattern recognition

Luis Sa-Couto, Andreas Wichert

Although deep learning has solved difficult problems in visual pattern recognition, it is mostly successful in tasks where there are lots of labeled training data available. Furthe…

cs.LG20206 cited

An Investigation of Interpretability Techniques for Deep Learning in Predictive Process Analytics

Catarina Moreira, Renuka Sindhgatta, Chun Ouyang +2

This paper explores interpretability techniques for two of the most successful learning algorithms in medical decision-making literature: deep neural networks and random forests. W…

cs.AI2018

Introducing Quantum-Like Influence Diagrams for Violations of the Sure Thing Principle

Catarina Moreira, Andreas Wichert

It is the focus of this work to extend and study the previously proposed quantum-like Bayesian networks to deal with decision-making scenarios by incorporating the notion of maximu…