Related papers: Integrating alignment-based and alignment-free seq…

Recent advances in deep learning have achieved impressive gains in classification accuracy on a variety of types of data, including images and text. Despite these gains, however, concerns have been raised about the calibration, robustness,…

Motivation: Receptor-binding proteins (RBPs) initiate viral infection and determine host specificity, serving as key targets for phage engineering and therapy. However, the identification of RBPs is complicated by their extreme sequence…

Modelling semantic similarity plays a fundamental role in lexical semantic applications. A natural way of calculating semantic similarity is to access handcrafted semantic networks, but similarity prediction can also be anticipated in a…

The success of self-supervised contrastive learning hinges on identifying positive data pairs, such that when they are pushed together in embedding space, the space encodes useful information for subsequent downstream tasks. Constructing…

The ability to quickly and accurately identify microbial species in a sample, known as metagenomic profiling, is critical across various fields, from healthcare to environmental science. This paper introduces a novel method to profile…

Longitudinal patient data has the potential to improve clinical risk stratification models for disease. However, chronic diseases that progress slowly over time are often heterogeneous in their clinical presentation. Patients may progress…

Motivation: DNA data is transcribed into single-stranded RNA, which folds into specific molecular structures. In this paper we pose the question to what extent sequence- and structure-information correlate. We view this correlation as…

We investigate the task of assessing sentence-level prompt relevance in learner essays. Various systems using word overlap, neural embeddings and neural compositional models are evaluated on two datasets of learner writing. We propose a new…

There is extensive interest in metric learning methods for image retrieval. Many metric learning loss functions focus on learning a correct ranking of training samples, but strongly overfit semantically inconsistent labels and require a…

Linearly transforming stimulus representations of deep neural networks yields high-performing models of behavioral and neural responses to complex stimuli. But does the test accuracy of such predictions identify genuine representational…

Existing saliency-guided training approaches improve model generalization by incorporating a loss term that compares the model's class activation map (CAM) for a sample's true-class ({\it i.e.}, correct-label class) against a human…

Deep metric learning applied to various applications has shown promising results in identification, retrieval and recognition. Existing methods often do not consider different granularity in visual similarity. However, in many domain…

Identifying clinically relevant biomarkers and developing predictive models are central challenges in biomedical research. Biomarkers are commonly used for disease screening, and some provide information not only on the presence or absence…

Multivariate time series alignment is critical for ensuring coherent analysis across variables, but missing values and timestamp inconsistencies make this task highly challenging. Existing approaches often rely on prior imputation, which…

Sequence discriminative training is a great tool to improve the performance of an automatic speech recognition system. It does, however, necessitate a sum over all possible word sequences, which is intractable to compute in practice.…

Multi-parametric MRI of the body is routinely acquired for the identification of abnormalities and diagnosis of diseases. However, a standard naming convention for the MRI protocols and associated sequences does not exist due to wide…

Molecular sequence analysis is crucial for comprehending several biological processes, including protein-protein interactions, functional annotation, and disease classification. The large number of sequences and the inherently complicated…

Capturing the similarities between human language units is crucial for explaining how humans associate different objects, and therefore its computation has received extensive attention, research, and applications. With the ever-increasing…

We introduce a new beam search decoder that is fully differentiable, making it possible to optimize at training time through the inference procedure. Our decoder allows us to combine models which operate at different granularities (e.g.…

Modern deep models are often pretrained on large-scale data with missing labels using composite objectives, where the relative weights of multiple loss terms act as hyperparameters. Tuning these weights with random search or Bayesian…