AIConfPaper
← Search

Ferran Alet

8 accepted papers

2021

A large-scale benchmark for few-shot program induction and synthesis

Ferran Alet, Javier Lopez-Contreras, James Koppel, Maxwell Nye, Armando Solar-Lezama, Tomas Lozano-Perez +2
ICML 2021spotlight

A landmark challenge for AI is to learn flexible, powerful representations from small numbers of examples. On an important class of tasks, hypotheses in the form of programs provide extreme generalization capabilities from surprisingly few examples. However, whereas large natural few-shot learning i…

Cited by 24Source ↗PDF ↗Scholar ↗
2021

Noether Networks: meta-learning useful conserved quantities

Ferran Alet, Dylan Doblar, Allan Zhou, Joshua B. Tenenbaum, Kenji Kawaguchi, Chelsea Finn
NeurIPS 2021poster

Progress in machine learning (ML) stems from a combination of data availability, computational resources, and an appropriate encoding of inductive biases. Useful biases often exploit symmetries in the prediction problem, such as convolutional networks relying on translation equivariance. Automatical…

Cited by 38Source ↗PDF ↗Scholar ↗
2021

Tailoring: encoding inductive biases by optimizing unsupervised objectives at prediction time

Ferran Alet, Maria Bauza Villalonga, Kenji Kawaguchi, Nurullah Giray Kuru, Tomas Perez, Leslie Pack Kaelbling
NeurIPS 2021poster

From CNNs to attention mechanisms, encoding inductive biases into neural networks has been a fruitful source of improvement in machine learning. Adding auxiliary losses to the main objective function is a general way of encoding biases that can help networks learn better representations. However, si…

Cited by 23Source ↗PDF ↗Scholar ↗
2019

Graph Element Networks: adaptive, structured computation and memory

Ferran Alet, Adarsh Keshav Jeewajee, Maria Bauza Villalonga, Alberto Rodriguez, Tomas Lozano-Perez, Leslie Kaelbling
ICML 2019oral

We explore the use of graph neural networks (GNNs) to model spatial processes in which there is no a priori graphical structure. Similar to finite element analysis, we assign nodes of a GNN to spatial locations and use a computational process defined on the graph to model the relationship between an…

Cited by 121Source ↗PDF ↗code ↗Scholar ↗
2019

Neural Relational Inference with Fast Modular Meta-learning

Ferran Alet, Erica Weng, Tomás Lozano-Pérez, Leslie Pack Kaelbling
NeurIPS 2019poster

Graph neural networks (GNNs) are effective models for many dynamical systems consisting of entities and relations. Although most GNN applications assume a single type of entity and relation, many situations involve multiple types of interactions. Relational inference is the problem of inferring thes…

Cited by 74Source ↗PDF ↗code ↗Scholar ↗
2019

Omnipush: accurate, diverse, real-world dataset of pushing dynamics with RGB-D video

Maria Bauza, Ferran Alet, Yen-Chen Lin, Tomás Lozano-Pérez, Leslie P. Kaelbling, Phillip Isola +1
IROS 2019poster

Pushing is a fundamental robotic skill. Existing work has shown how to exploit models of pushing to achieve a variety of tasks, including grasping under uncertainty, in-hand manipulation and clearing clutter. Such models, however, are approximate, which limits their applicability.Learning-based meth…

Cited by 26Source ↗Scholar ↗
2018

Robotic Pick-and-Place of Novel Objects in Clutter with Multi-Affordance Grasping and Cross-Domain Image Matching

Andy Zeng, Shuran Song, Kuan-Ting Yu, Elliott Donlon, Francois R. Hogan, Maria Bauza +15
ICRA 2018poster

This paper presents a robotic pick-and-place system that is capable of grasping and recognizing both known and novel objects in cluttered environments. The key new feature of the system is that it handles a wide range of object categories without needing any task-specific training data for novel obj…

Cited by 848Source ↗code ↗Scholar ↗