Related papers: DeepSeer: Interactive RNN Explanation and Debuggin…

Nowadays, deep neural networks are widely used in a variety of fields that have a direct impact on society. Although those models typically show outstanding performance, they have been used for a long time as black boxes. To address this,…

Deep learning (DL) has emerged as a promising tool to downscale climate projections at regional-to-local scales from large-scale atmospheric fields following the perfect-prognosis (PP) approach. Given their complexity, it is crucial to…

We propose Neural Reasoner, a framework for neural network-based reasoning over natural language sentences. Given a question, Neural Reasoner can infer over multiple supporting facts and find an answer to the question in specific forms.…

Deep neural network models represent the state-of-the-art methodologies for natural language processing. Here we build on top of these methodologies to incorporate temporal information and model how to review data changes with time.…

Recently, several methods have been proposed to explain the predictions of recurrent neural networks (RNNs), in particular of LSTMs. The goal of these methods is to understand the network's decisions by assigning to each input variable,…

Graph Neural Networks (GNNs) are a powerful technique for machine learning on graph-structured data, yet they pose challenges in interpretability. Existing GNN explanation methods usually yield technical outputs, such as subgraphs and…

While large language models (LLMs) excel in mathematical and code reasoning, we observe they struggle with social reasoning tasks, exhibiting cognitive confusion, logical inconsistencies, and conflation between objective world states and…

Machine learning models have been successfully applied to a wide range of applications including computer vision, natural language processing, and speech recognition. A successful implementation of these models however, usually relies on…

This paper introduces a novel XAI approach based on near-misses analysis (NMA). This approach reveals a hierarchy of logical 'concepts' inferred from the latent decision-making process of a Neural Network (NN) without delving into its…

With the constant increase of available data in various domains, such as the Internet of Things, Social Networks or Smart Cities, it has become fundamental that agents are able to process and reason with such data in real time. Whereas…

Deep Recurrent Neural Network (RNN) has gained popularity in many sequence classification tasks. Beyond predicting a correct class for each data instance, data scientists also want to understand what differentiating factors in the data have…

Spoken Language Understanding (SLU) typically comprises of an automatic speech recognition (ASR) followed by a natural language understanding (NLU) module. The two modules process signals in a blocking sequential fashion, i.e., the NLU…

The success of recent deep convolutional neural networks (CNNs) depends on learning hidden representations that can summarize the important factors of variation behind the data. However, CNNs often criticized as being black boxes that lack…

Deep learning, a branch of artificial intelligence, is a data-driven method that uses multiple layers of interconnected units or neurons to learn intricate patterns and representations directly from raw input data. Empowered by this…

This work aims at shedding some light on connections between finite state machines (FSMs), and recurrent neural networks (RNNs). Examined connections in this master's thesis is threefold: the extractability of finite state machines from…

Despite the high accuracy offered by state-of-the-art deep natural-language models (e.g. LSTM, BERT), their application in real-life settings is still widely limited, as they behave like a black-box to the end-user. Hence, explainability is…

Explainable AI (XAI) has become essential in computer vision to make the decision-making processes of deep learning models transparent. However, current visual explanation (XAI) methods face a critical trade-off between the high fidelity of…

Many real-world datasets are time series that are sequentially collected and contain rich temporal information. Thus, a common interest in practice is to capture dynamics of time series and predict their future evolutions. To this end, the…

To be effective in sequential data processing, Recurrent Neural Networks (RNNs) are required to keep track of past events by creating memories. While the relation between memories and the network's hidden state dynamics was established over…

Although Deep Neural Networks (DNNs) have great generalization and prediction capabilities, their functioning does not allow a detailed explanation of their behavior. Opaque deep learning models are increasingly used to make important…