Related papers: Optimizing fMRI Data Acquisition for Decoding Natu…

Deep learning is often applied in settings where data are limited, correlated, and difficult to obtain, yet evaluation practices do not always reflect these constraints. Neuroimaging for prodromal Parkinsons disease is one such case, where…

Fine-tuning Large Language Models (LLMs) incurs considerable training costs, driving the need for data-efficient training with optimised data ordering. Human-inspired strategies offer a solution by organising data based on human learning…

The connection between brain activity and corresponding visual stimuli is crucial in comprehending the human brain. While deep generative models have exhibited advancement in recovering brain recordings by generating images conditioned on…

While deep learning techniques have shown promising results in many natural language processing (NLP) tasks, it has not been widely applied to the clinical domain. The lack of large datasets and the pervasive use of domain-specific language…

Unsupervised methods for learning distributed representations of words are ubiquitous in today's NLP research, but far less is known about the best ways to learn distributed phrase or sentence representations from unlabelled data. This…

Multi-frame algorithms for single-channel speech enhancement are able to take advantage from short-time correlations within the speech signal. Deep Filtering (DF) was proposed to directly estimate a complex filter in frequency domain to…

Objective: Few-shot learning (FSL) methods require small numbers of labeled instances for training. As many medical topics have limited annotated textual data in practical settings, FSL-based natural language processing (NLP) methods hold…

Interactions with virtual assistants typically start with a predefined trigger phrase followed by the user command. To make interactions with the assistant more intuitive, we explore whether it is feasible to drop the requirement that users…

Among the most impressive recent applications of neural decoding is the visual representation decoding, where the category of an object that a subject either sees or imagines is inferred by observing his/her brain activity. Even though…

Personalized vision-language retrieval seeks to recognize new concepts (e.g. "my dog Fido") from only a few examples. This task is challenging because it requires not only learning a new concept from a few images, but also integrating the…

Deep learning models usually require sufficient training data to achieve high accuracy, but obtaining labeled data can be time-consuming and labor-intensive. Here we introduce a template-based training method to train a 3D U-Net model from…

Functional MRI data exhibit high-dimensional spatiotemporal structure, making both prediction and decoding challenging. In this work, we investigate neural integral-operator-based models for encoding and decoding tasks in fMRI, with…

Most deep learning-based multi-channel speech enhancement methods focus on designing a set of beamforming coefficients to directly filter the low signal-to-noise ratio signals received by microphones, which hinders the performance of these…

Despite the recent success of deep neural networks in natural language processing (NLP), their interpretability remains a challenge. We analyze the representations learned by neural machine translation models at various levels of…

Deep learning usually achieves the best results with complete supervision. In the case of semantic segmentation, this means that large amounts of pixelwise annotations are required to learn accurate models. In this paper, we show that we…

Deep learning based speech denoising still suffers from the challenge of improving perceptual quality of enhanced signals. We introduce a generalized framework called Perceptual Ensemble Regularization Loss (PERL) built on the idea of…

Adapting language models (LMs) to novel domains is often achieved through fine-tuning a pre-trained LM (PLM) on domain-specific data. Fine-tuning introduces new knowledge into an LM, enabling it to comprehend and efficiently perform a…

Most recent neural semi-supervised learning algorithms rely on adding small perturbation to either the input vectors or their representations. These methods have been successful on computer vision tasks as the images form a continuous…

Deep neural networks and huge language models are becoming omnipresent in natural language applications. As they are known for requiring large amounts of training data, there is a growing body of work to improve the performance in…

Modern language models operate on subword-tokenized text in order to make a trade-off between model size, inference speed, and vocabulary coverage. A side effect of this is that, during inference, models are evaluated by measuring the…