Related papers: META$^\mathbf{2}$: Memory-efficient taxonomic clas…
Metagenomics is an emerging field of molecular biology concerned with analyzing the genomes of environmental samples comprising many different diverse organisms. Given the nature of metagenomic data, one usually has to sequence the genomic…
At its core, this thesis aims to enhance the practicality of deep learning by improving the label and training efficiency of deep learning models. To this end, we investigate data subset selection techniques, specifically active learning…
Deep learning has significantly advanced medical imaging analysis (MIA), achieving state-of-the-art performance across diverse clinical tasks. However, its success largely depends on large-scale, high-quality labeled datasets, which are…
A key obstacle in automated analytics and meta-learning is the inability to recognize when different datasets contain measurements of the same variable. Because provided attribute labels are often uninformative in practice, this task may be…
Background and objective: Employing deep learning models in critical domains such as medical imaging poses challenges associated with the limited availability of training data. We present a strategy for improving the performance and…
Efficient custom pooling techniques that can aggressively trim the dimensions of a feature map and thereby reduce inference compute and memory footprint for resource-constrained computer vision applications have recently gained significant…
One possible approach to tackle the class imbalance in classification tasks is to resample a training dataset, i.e., to drop some of its elements or to synthesize new ones. There exist several widely-used resampling methods. Recent research…
Autonomous agents interacting with the real world need to learn new concepts efficiently and reliably. This requires learning in a low-data regime, which is a highly challenging problem. We address this task by introducing a fast…
Automated analysis of tissue sections allows a better understanding of disease biology and may reveal biomarkers that could guide prognosis or treatment selection. In digital pathology, less abundant cell types can be of biological…
A fundamental challenge in developing data-driven approaches to ecological systems for tasks such as state estimation and prediction is the paucity of the observational or measurement data. For example, modern machine-learning techniques…
Recent advancements in deep learning have brought significant improvements to plant disease recognition. However, achieving satisfactory performance often requires high-quality training datasets, which are challenging and expensive to…
Deep Neural Networks (DNN's) are a widely-used solution for a variety of machine learning problems. However, it is often necessary to invest a significant amount of a data scientist's time to pre-process input data, test different neural…
Insect monitoring is crucial for understanding the consequences of rapid ecological changes, but taxa identification currently requires tedious manual expert work and cannot be scaled-up efficiently. Deep convolutional neural networks…
A basic problem in metagenomics is to assign a sequenced read to the correct species in the reference collection. In typical applications in genomic epidemiology and viral metagenomics the reference collection consists of set of species…
Medical professionals frequently work in a data constrained setting to provide insights across a unique demographic. A few medical observations, for instance, informs the diagnosis and treatment of a patient. This suggests a unique setting…
The research explores the utilization of a deep learning model employing an attention mechanism in medical text mining. It targets the challenge of analyzing unstructured text information within medical data. This research seeks to enhance…
Representations for black-box optimisation methods (such as evolutionary algorithms) are traditionally constructed using a delicate manual process. This is in contrast to the representation that maps DNAs to phenotypes in biological…
Machine comprehension(MC) style question answering is a representative problem in natural language processing. Previous methods rarely spend time on the improvement of encoding layer, especially the embedding of syntactic information and…
The large volumes of sequencing data required to sample complex environments deeply pose new challenges to sequence analysis approaches. De novo metagenomic assembly effectively reduces the total amount of data to be analyzed but requires…
Majority of the modern meta-learning methods for few-shot classification tasks operate in two phases: a meta-training phase where the meta-learner learns a generic representation by solving multiple few-shot tasks sampled from a large…