Related papers: Explainability of Recurrent Neural Networks for En…

In this work, we analyze the capabilities and practical limitations of neural networks (NNs) for sequence-based signal processing which can be seen as an omnipresent property in almost any modern communication systems. In particular, we…

Existing deep learning models for Predictive Process Monitoring (PPM) struggle with temporal irregularities, particularly stochastic event durations and overlapping timestamps, limiting their adaptability across heterogeneous datasets. We…

Conventionally, AI models are thought to trade off explainability for lower accuracy. We develop a training strategy that not only leads to a more explainable AI system for object classification, but as a consequence, suffers no perceptible…

Function and dysfunctions of neural systems are tied to the temporal evolution of neural states. The current limitations in showing their causal role stem largely from the absence of tools capable of probing the brain's internal state in…

In sequence learning tasks such as language modelling, Recurrent Neural Networks must learn relationships between input features separated by time. State of the art models such as LSTM and Transformer are trained by backpropagation of…

We have developed a graphic user interface (GUI), ExBrainable, dedicated to convolutional neural networks (CNN) model training and visualization in electroencephalography (EEG) decoding. Available functions include model training,…

Implicit Neural Representations (INRs) have revolutionized signal processing and computer vision by modeling signals as continuous, differentiable functions parameterized by neural networks. However, INRs are prone to the spectral bias…

Brain-computer interfaces (BCIs) enable direct communication between the brain and external devices, providing critical support for individuals with motor impairments. However, accurate motor imagery (MI) decoding from…

Noninvasive brain computer interfaces (BCI), and more specifically Electroencephalography (EEG) based systems for intent detection need to compensate for the low signal to noise ratio of EEG signals. In many applications, the temporal…

Robotic arms are increasingly being used in collaborative environments, requiring an accurate understanding of human intentions to ensure both effectiveness and safety. Electroencephalogram (EEG) signals, which measure brain activity,…

Deep learning methods have shown great success in several domains as they process a large amount of data efficiently, capable of solving complex classification, forecast, segmentation, and other tasks. However, they come with the inherent…

Understanding the internal dynamics of Recurrent Neural Networks (RNNs) is crucial for advancing their interpretability and improving their design. This study introduces an innovative information-theoretic method to identify and analyze…

Compared with traditional deep learning techniques, continual learning enables deep neural networks to learn continually and adaptively. Deep neural networks have to learn new tasks and overcome forgetting the knowledge obtained from the…

One of the challenges in modeling cognitive events from electroencephalogram (EEG) data is finding representations that are invariant to inter- and intra-subject differences, as well as to inherent noise associated with such data. Herein,…

Deep neural networks, including recurrent networks, have been successfully applied to human activity recognition. Unfortunately, the final representation learned by recurrent networks might encode some noise (irrelevant signal components,…

Transformers process tokens in parallel but are temporally shallow: at position $t$, each layer attends to key-value pairs computed based on the previous layer, yielding a depth capped by the number of layers. Recurrent models offer…

Recurrent neural networks have proven effective in modeling sequential user feedbacks for recommender systems. However, they usually focus solely on item relevance and fail to effectively explore diverse items for users, therefore harming…

We introduce provenance networks, a novel class of neural models designed to provide end-to-end, training-data-driven explainability. Unlike conventional post-hoc methods, provenance networks learn to link each prediction directly to its…

Deep learning has significantly advanced electrocardiogram (ECG) analysis, enabling automatic annotation, disease screening, and prognosis beyond traditional clinical capabilities. However, understanding these models remains a challenge,…

Ability of deep networks to extract high level features and of recurrent networks to perform time-series inference have been studied. In view of universality of one hidden layer network at approximating functions under weak constraints, the…