LGCVOct 12, 2021

Dynamic Inference with Neural Interpreters

arXiv:2110.06399v133 citations
Originality Highly original
AI Analysis

This addresses the challenge of compositional reasoning for AI systems, offering a novel approach to improve generalization beyond training distributions.

The paper tackles the problem of systematic generalization in neural networks by proposing Neural Interpreters, an architecture that factorizes inference into modular functions, achieving competitive performance in image classification with fewer parameters and in visual abstract reasoning.

Modern neural network architectures can leverage large amounts of data to generalize well within the training distribution. However, they are less capable of systematic generalization to data drawn from unseen but related distributions, a feat that is hypothesized to require compositional reasoning and reuse of knowledge. In this work, we present Neural Interpreters, an architecture that factorizes inference in a self-attention network as a system of modules, which we call \emph{functions}. Inputs to the model are routed through a sequence of functions in a way that is end-to-end learned. The proposed architecture can flexibly compose computation along width and depth, and lends itself well to capacity extension after training. To demonstrate the versatility of Neural Interpreters, we evaluate it in two distinct settings: image classification and visual abstract reasoning on Raven Progressive Matrices. In the former, we show that Neural Interpreters perform on par with the vision transformer using fewer parameters, while being transferrable to a new task in a sample efficient manner. In the latter, we find that Neural Interpreters are competitive with respect to the state-of-the-art in terms of systematic generalization

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes