activity
20172022
most citedEnvironmental drivers of systematicity and generalization in a situated agent

53 citations · 78 across the 4 of their papers we have counts for

collaborators

9 papers

cs.CL202211 cited

Transformers generalize differently from information stored in context vs in weights

Stephanie C. Y. Chan, Ishita Dasgupta, Junkyung Kim +3

Transformer models can use two fundamentally different kinds of information: information stored in weights during training, and information provided ``in-context'' at inference tim…

cs.LG2020

What shapes feature representations? Exploring datasets, architectures, and training

Katherine L. Hermann, Andrew K. Lampinen

In naturalistic learning problems, a model's input contains a wide range of features, some useful for the task at hand, and others not. Of the useful features, which ones does the…

cs.LG2020

Transforming task representations to perform novel tasks

Andrew K. Lampinen, James L. McClelland

An important aspect of intelligence is the ability to adapt to a novel task without any direct experience (zero-shot), based on its relationship to previous tasks. Humans can exhib…

cs.AI201953 cited

Environmental drivers of systematicity and generalization in a situated agent

Felix Hill, Andrew Lampinen, Rosalia Schneider +4

The question of whether deep neural networks are good at generalising beyond their immediate training experience is of critical importance for learning-based approaches to AI. Here…

cs.LG2019

Automated curricula through setter-solver interactions

Sebastien Racaniere, Andrew K. Lampinen, Adam Santoro +3

Reinforcement learning algorithms use correlations between policies and rewards to improve agent performance. But in dynamic or sparsely rewarding environments these correlations a…

cs.LG2019

Zero-shot task adaptation by homoiconic meta-mapping

Andrew K. Lampinen, James L. McClelland

How can deep learning systems flexibly reuse their knowledge? Toward this goal, we propose a new class of challenges, and a class of architectures that can solve them. The challeng…