Related papers: Neural Pre-Processing: A Learning Framework for En…

Segmentation is one of the most important tasks in MRI medical image analysis and is often the first and the most critical step in many clinical applications. In brain MRI analysis, head segmentation is commonly used for measuring and…

This paper aims to compare different regularization strategies to address a common phenomenon, severe overfitting, in embedding-based neural networks for NLP. We chose two widely studied neural models and tasks as our testbed. We tried…

Recent fMRI-to-image approaches mainly focused on associating fMRI signals with specific conditions of pre-trained diffusion models. These approaches, while producing high-quality images, capture only a limited aspect of the complex…

End-to-end learning has become a widely applicable and studied problem in training predictive ML models to be aware of their impact on downstream decision-making tasks. These end-to-end models often outperform traditional methods that…

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…

Representing a signal as a continuous function parameterized by neural network (a.k.a. Implicit Neural Representations, INRs) has attracted increasing attention in recent years. Neural Processes (NPs), which model the distributions over…

Most uses of machine learning today involve training a model from scratch for a particular task, or sometimes starting with a model pretrained on a related task and then fine-tuning on a downstream task. Both approaches offer limited…

Machine Learning (ML) is increasingly being used for computer aided diagnosis of brain related disorders based on structural magnetic resonance imaging (MRI) data. Most of such work employs biologically and medically meaningful hand-crafted…

Machine learning-based seismic processing models are typically trained separately to perform specific seismic processing tasks (SPTs), and as a result, require plenty of training data. However, preparing training data sets is not trivial,…

To enable DNNs on edge devices like mobile phones, low-rank approximation has been widely adopted because of its solid theoretical rationale and efficient implementations. Several previous works attempted to directly approximate a…

Skull-stripping separates the skull region of the head from the soft brain tissues. In many cases of brain image analysis, this is an essential preprocessing step in order to improve the final result. This is true for both registration and…

End-to-end autonomous driving has emerged as a dominant paradigm, yet its highly entangled black-box models pose significant challenges in terms of interpretability and safety assurance. To improve model transparency and training…

We propose multirate training of neural networks: partitioning neural network parameters into "fast" and "slow" parts which are trained on different time scales, where slow parts are updated less frequently. By choosing appropriate…

Raven's Progressive Matrices (RPM) have been widely used for Intelligence Quotient (IQ) test of humans. In this paper, we aim to solve RPM with neural networks in both supervised and unsupervised manners. First, we investigate strategies to…

Deep learning has largely improved the performance of various natural language processing (NLP) tasks. However, most deep learning models are black-box machinery, and lack explicit interpretation. In this chapter, we will introduce our…

Skull stripping magnetic resonance images (MRI) of the human brain is an important process in many image processing techniques, such as automatic segmentation of brain structures. Numerous methods have been developed to perform this task,…

In this paper, we present a Neural Preset technique to address the limitations of existing color style transfer methods, including visual artifacts, vast memory requirement, and slow style switching speed. Our method is based on two core…

A core goal of functional neuroimaging is to study how the environment is processed in the brain. The mainstream paradigm involves concurrently measuring a broad spectrum of brain responses to a small set of environmental features…

Training deep neural networks from scratch on natural language processing (NLP) tasks requires significant amount of manually labeled text corpus and substantial time to converge, which usually cannot be satisfied by the customers. In this…

We introduce Scaffold Prompt Tuning (ScaPT), a novel prompt-based framework for adapting large-scale functional magnetic resonance imaging (fMRI) pre-trained models to downstream tasks, with high parameter efficiency and improved…