Related papers: Feature Importance Estimation with Self-Attention …

Interpretability is an important area of research for safe deployment of machine learning systems. One particular type of interpretability method attributes model decisions to input features. Despite active development, quantitative…

Deep neural networks (DNNs) demonstrate outstanding performance across most computer vision tasks. Some critical applications, such as autonomous driving or medical imaging, also require investigation into their behavior and the reasons…

Aiming at the problems that the convolutional neural networks neglect to capture the inherent attributes of natural images and extract features only in a single scale in the field of image super-resolution reconstruction, a network…

In this work, we propose three explainable deep learning architectures to automatically detect patients with Alzheimer`s disease based on their language abilities. The architectures use: (1) only the part-of-speech features; (2) only…

Multi-view multi-label data offers richer perspectives for artificial intelligence, but simultaneously presents significant challenges for feature selection due to the inherent complexity of interrelations among features, views and labels.…

Understanding how Large Language Models (LLMs) process information from prompts remains a significant challenge. To shed light on this "black box," attention visualization techniques have been developed to capture neuron-level perceptions…

In humans, Attention is a core property of all perceptual and cognitive operations. Given our limited ability to process competing sources, attention mechanisms select, modulate, and focus on the information most relevant to behavior. For…

A new method for local and global explanation of the machine learning black-box model predictions by tabular data is proposed. It is implemented as a system called AFEX (Attention-like Feature EXplanation) and consisting of two main parts.…

As an alternative to question answering methods based on feature engineering, deep learning approaches such as convolutional neural networks (CNNs) and Long Short-Term Memory Models (LSTMs) have recently been proposed for semantic matching…

Recent deep-learning models have achieved impressive predictive performance by learning complex functions of many variables, often at the cost of interpretability. This chapter covers recent work aiming to interpret models by attributing…

Visual attention mechanisms have proven to be integrally important constituent components of many modern deep neural architectures. They provide an efficient and effective way to utilize visual information selectively, which has shown to be…

Attention mechanisms, which enable a neural network to accurately focus on all the relevant elements of the input, have become an essential component to improve the performance of deep neural networks. There are mainly two attention…

Attention is an increasingly popular mechanism used in a wide range of neural architectures. The mechanism itself has been realized in a variety of formats. However, because of the fast-paced advances in this domain, a systematic overview…

The Transformer-based models with the multi-head self-attention mechanism are widely used in natural language processing, and provide state-of-the-art results. While the pre-trained language backbones are shown to implicitly capture certain…

In this paper, we address the "black-box" problem in predictive process analytics by building interpretable models that are capable to inform both what and why is a prediction. Predictive process analytics is a newly emerged discipline…

Visual attention has been extensively studied for learning fine-grained features in both facial expression recognition (FER) and Action Unit (AU) detection. A broad range of previous research has explored how to use attention modules to…

There has been significant debate in the NLP community about whether or not attention weights can be used as an explanation - a mechanism for interpreting how important each input token is for a particular prediction. The validity of…

Attention mechanisms are a central property of cognitive systems allowing them to selectively deploy cognitive resources in a flexible manner. Attention has been long studied in the neurosciences and there are numerous phenomenological…

Convolutional Neural Networks (CNNs) have been the standard for image classification tasks for a long time, but more recently attention-based mechanisms have gained traction. This project aims to compare traditional CNNs with…

Advanced automated AI techniques allow us to classify protein sequences and discern their biological families and functions. Conventional approaches for classifying these protein families often focus on extracting N-Gram features from the…