paper-with-me

홈 › Papers

Causal Learning and Explanation of Deep Neural Networks via Autoencoded Activations

2018-02-02 · Michael Harradon, Jeff Druce, Brian Ruttenberg

Deep neural networks are complex and opaque. As they enter application in a variety of important and safety critical domains, users seek methods to explain their output predictions. We develop an approach to explaining deep neural networks by constructing causal models on salient concepts contained in a CNN. We develop methods to extract salient concepts throughout a target network by using autoencoders trained to extract human-understandable representations of network activations. We then build a bayesian causal model using these extracted concepts as variables in order to explain image classification. Finally, we use this causal model to identify and visualize features with significant causal influence on final classification.

📄 PDF Abstract BibTeX arXiv:1802.00541

Code (0)

등록된 구현이 없습니다.

Tasks

ClassificationGeneral Classificationimage-classificationImage Classification

Similar Papers 제목 키워드 기반

Linear Explanations for Individual Neurons

2024-05-10 · Tuomas Oikarinen, Tsui-Wei Weng

In recent years many methods have been developed to understand the internal workings of neural networks, often by describing the function of individual neurons in the model. However, these methods typically only focus on…

Neural Networks Decoded: Targeted and Robust Analysis of Neural Network Decisions via Causal Explanations and Reasoning

2024-10-07 · Alec F. Diallo, Vaishak Belle, Paul Patras

Despite their success and widespread adoption, the opaque nature of deep neural networks (DNNs) continues to hinder trust, especially in critical applications. Current interpretability solutions often yield inconsistent …

Causal Inference

Causal Interpretation of Sparse Autoencoder Features in Vision

2025-08-31 · Sangyu Han, Yearim Kim, Nojun Kwak arxiv

Understanding what sparse auto-encoder (SAE) features in vision transformers truly represent is usually done by inspecting the patches where a feature's activation is highest. However, self-attention mixes information ac…

N2D: (Not Too) Deep Clustering via Clustering the Local Manifold of an Autoencoded Embedding

2019-08-16 · Ryan McConville, Raul Santos-Rodriguez, Robert J. Piechocki, Ian Craddock

Deep clustering has increasingly been demonstrating superiority over conventional shallow clustering algorithms. Deep clustering algorithms usually combine representation learning with deep neural networks to achieve thi…

ClusteringDeep ClusteringImage ClusteringRepresentation Learning+3

Attention Sinks Induce Gradient Sinks: Massive Activations as Gradient Regulators in Transformers

2026-03-18 · Yihong Chen, Zhouchen Lin, Quanming Yao arxiv

Attention sinks and massive activations are recurring and closely related phenomena in Transformer models. Existing explanations have largely focused on the forward pass, yet in pre-norm Transformers, large residual-stre…