Related papers: nnterp: A Standardized Interface for Mechanistic I…
In data-driven applications relying on tabular data, where interpretability is key, machine learning models such as decision trees and linear regression are applied. Although neural networks can provide higher predictive performance, they…
Transformers have revolutionized machine learning, yet their inner workings remain opaque to many. We present Transformer Explainer, an interactive visualization tool designed for non-experts to learn about Transformers through the GPT-2…
Visual transformers have achieved remarkable performance in image classification tasks, but this performance gain has come at the cost of interpretability. One of the main obstacles to the interpretation of transformers is the…
Transformers have supplanted recurrent models in a large number of NLP tasks. However, the differences in their abilities to model different syntactic properties remain largely unknown. Past works suggest that LSTMs generalize very well on…
Person re-identification aims to retrieve persons in highly varying settings across different cameras and scenarios, in which robust and discriminative representation learning is crucial. Most research considers learning representations…
In recent years, many interpretability methods have been proposed to help interpret the internal states of Transformer-models, at different levels of precision and complexity. Here, to analyze encoder-decoder Transformers, we propose a…
Mechanistic interpretability aims to understand the computational mechanisms underlying neural networks' capabilities in order to accomplish concrete scientific and engineering goals. Progress in this field thus promises to provide greater…
What is the computational model behind a Transformer? Where recurrent neural networks have direct parallels in finite state machines, allowing clear discussion and thought around architecture variants or trained models, Transformers have no…
Transformer-based models have transformed the landscape of natural language processing (NLP) and are increasingly applied to computer vision tasks with remarkable success. These models, renowned for their ability to capture long-range…
adaptNMT streamlines all processes involved in the development and deployment of RNN and Transformer neural translation models. As an open-source application, it is designed for both technical and non-technical users who work in the field…
The interpretability of neural networks has recently received extensive attention. Previous prototype-based explainable networks involved prototype activation in both reasoning and interpretation processes, requiring specific explainable…
We show a proof of principle for warping, a method to interpret the inner working of neural networks in the context of gene expression analysis. Warping is an efficient way to gain insight to the inner workings of neural nets and make them…
Deep learning based transient stability assessment (TSA) has achieved great success, yet the lack of interpretability hinders its industrial application. Although a great number of studies have tried to explore the interpretability of…
Attention matrices are fundamental to transformer research, supporting a broad range of applications including interpretability, visualization, manipulation, and distillation. Yet, most existing analyses focus on individual attention heads…
Transformers are the dominant architecture in NLP, but their training and fine-tuning is still very challenging. In this paper, we present the design and implementation of a visual analytic framework for assisting researchers in such…
Integrating General Models (GMs) such as Large Language Models (LLMs), with Specialized Models (SMs) in autonomous driving tasks presents a promising approach to mitigating challenges in data diversity and model capacity of existing…
We propose a novel neural network architecture, the normalized Transformer (nGPT) with representation learning on the hypersphere. In nGPT, all vectors forming the embeddings, MLP, attention matrices and hidden states are unit norm…
With the increasing application of deep learning algorithms to time series classification, especially in high-stake scenarios, the relevance of interpreting those algorithms becomes key. Although research in time series interpretability has…
Large Language Models such as GPTs (Generative Pre-trained Transformers) exhibit remarkable capabilities across a broad spectrum of applications. Nevertheless, due to their intrinsic complexity, these models present substantial challenges…
While transformer-based models have achieved state-of-the-art results in a variety of classification and generation tasks, their black-box nature makes them challenging for interpretability. In this work, we present a novel visual…