Related papers: Bias Reduction via End-to-End Shift Learning: Appl…

in healthcare. However, the existing AI model may be biased in its decision marking. The bias induced by data itself, such as collecting data in subgroups only, can be mitigated by including more diversified data. Distributed and…

Convolutional neural networks (CNN) have been successful in machine learning applications. Their success relies on their ability to consider space invariant local features. We consider the use of CNN to fit nuisance models in semiparametric…

Recent developments using End-to-End Deep Learning models have been shown to have near or better performance than state of the art Recurrent Neural Networks (RNNs) on Automatic Speech Recognition tasks. These models tend to be lighter…

Unsupervised crowd counting is a challenging yet not largely explored task. In this paper, we explore it in a transfer learning setting where we learn to detect and count persons in an unlabeled target set by transferring bi-knowledge…

The prediction of saliency areas in images has been traditionally addressed with hand crafted features based on neuroscience principles. This paper however addresses the problem with a completely data-driven approach by training a…

Machine learning systems often acquire biases by leveraging undesired features in the data, impacting accuracy variably across different sub-populations. Current understanding of bias formation mostly focuses on the initial and final stages…

Common computational methods for automated eye movement detection - i.e. the task of detecting different types of eye movement in a continuous stream of gaze data - are limited in that they either involve thresholding on hand-crafted signal…

Optimal decision making requires that classifiers produce uncertainty estimates consistent with their empirical accuracy. However, deep neural networks are often under- or over-confident in their predictions. Consequently, methods have been…

Deep learning algorithms mine knowledge from the training data and thus would likely inherit the dataset's bias information. As a result, the obtained model would generalize poorly and even mislead the decision process in real-life…

Projector photometric compensation aims to modify a projector input image such that it can compensate for disturbance from the appearance of projection surface. In this paper, for the first time, we formulate the compensation problem as an…

We propose a novel end-to-end neural network architecture that, once trained, directly outputs a probabilistic clustering of a batch of input examples in one pass. It estimates a distribution over the number of clusters $k$, and for each $1…

Code-switching (CS) refers to a linguistic phenomenon where a speaker uses different languages in an utterance or between alternating utterances. In this work, we study end-to-end (E2E) approaches to the Mandarin-English code-switching…

Using transfer learning to adapt a pre-trained "source model" to a downstream "target task" can dramatically increase performance with seemingly no downside. In this work, we demonstrate that there can exist a downside after all: bias…

We propose an end-to-end ensemble method for person re-identification (ReID) to address the problem of overfitting in discriminative models. These models are known to converge easily, but they are biased to the training data in general and…

Machine learning on data streams is increasingly more present in multiple domains. However, there is often data distribution shift that can lead machine learning models to make incorrect decisions. While there are automatic methods to…

Few-Shot Classification(FSC) aims to generalize from base classes to novel classes given very limited labeled samples, which is an important step on the path toward human-like machine learning. State-of-the-art solutions involve learning to…

This paper presents a novel cloud-edge framework for addressing computational and energy constraints in complex control systems. Our approach centers around a learning-based controller using Spiking Neural Networks (SNN) on physical plants.…

Traditional causal inference approaches leverage observational study data to estimate the difference in observed and unobserved outcomes for a potential treatment, known as the Conditional Average Treatment Effect (CATE). However, CATE…

In the last few years, contributions of the general public in scientific projects has increased due to the advancement of communication and computing technologies. Internet played an important role in connecting scientists and volunteers…

With the prosperity of mobile devices, the distributed learning approach enabling model training with decentralized data has attracted wide research. However, the lack of training capability for edge devices significantly limits the energy…