Latent Attention Networks

by   Christopher Grimm, et al.

Deep neural networks are able to solve tasks across a variety of domains and modalities of data. Despite many empirical successes, we lack the ability to clearly understand and interpret the learned internal mechanisms that contribute to such effective behaviors or, more critically, failure modes. In this work, we present a general method for visualizing an arbitrary neural network's inner mechanisms and their power and limitations. Our dataset-centric method produces visualizations of how a trained network attends to components of its inputs. The computed "attention masks" support improved interpretability by highlighting which input attributes are critical in determining output. We demonstrate the effectiveness of our framework on a variety of deep neural network architectures in domains from computer vision, natural language processing, and reinforcement learning. The primary contribution of our approach is an interpretable visualization of attention that provides unique insights into the network's underlying decision-making process irrespective of the data modality.


page 5

page 6

page 8


iNNvestigate neural networks!

In recent years, deep neural networks have revolutionized many applicati...

VL-InterpreT: An Interactive Visualization Tool for Interpreting Vision-Language Transformers

Breakthroughs in transformer-based models have revolutionized not only t...

Learning to Deceive with Attention-Based Explanations

Attention mechanisms are ubiquitous components in neural architectures a...

Analysis of Explainers of Black Box Deep Neural Networks for Computer Vision: A Survey

Deep Learning is a state-of-the-art technique to make inference on exten...

D2RL: Deep Dense Architectures in Reinforcement Learning

While improvements in deep learning architectures have played a crucial ...

Deep Adaptive Wavelet Network

Even though convolutional neural networks have become the method of choi...

Reversible Architectures for Arbitrarily Deep Residual Neural Networks

Recently, deep residual networks have been successfully applied in many ...