← Search

Julio Hurtado

3 accepted papers

2025

Data Distributional Properties As Inductive Bias for Systematic Generalization

CVPR 2025poster

Deep neural networks (DNNs) struggle at systematic generalization (SG). Several studies have evaluated the possibility of promoting SG through the proposal of novel architectures, loss functions, or training methodologies. Few studies, however, have focused on the role of training data properties in…

2023

PIVOT: Prompting for Video Continual Learning

CVPR 2023poster

Modern machine learning pipelines are limited due to data availability, storage quotas, privacy regulations, and expensive annotation processes. These constraints make it difficult or impossible to train and update large-scale models on such dynamic annotated sets. Continual learning directly approa…

Cited by 60SourcePDFScholar
2021

Optimizing Reusable Knowledge for Continual Learning via Metalearning

NeurIPS 2021poster

When learning tasks over time, artificial neural networks suffer from a problem known as Catastrophic Forgetting (CF). This happens when the weights of a network are overwritten during the training of a new task causing forgetting of old information. To address this issue, we propose MetA Reusable K…