Search

Knowledge transferability, or transfer learning, has been widely adopted to allow a pre-trained model in the source domain to be effectively adapted to downstream tasks in the target domain. It is thus important to explore and understand the factors affecting knowledge transferability. In this paper...

Natural language processing (NLP) systems have become a central technology in communication, education, medicine, artificial intelligence, and many other domains of research and development. While the performance of NLP methods has grown enormously over the last decade, this progress has been...

(This article originally appeared on JF Gagne's blog here.)

Self-regulation doesn’t work. The interests of business are too narrow, and it is too easy for them to say better practices are too hard. Our narratives about business and technology further abstract away the power the makers and owners...

Marketing scientist Kevin Gray asks Dr. Anna Farzindar of the University of Southern California for a snapshot of machine translation. Dr. Farzindar also provided the original art for this article.

Despite their ability to represent highly expressive functions, deep learning models trained with SGD seem to find simple, constrained solutions that generalize surprisingly well. Spectral bias - the tendency of neural networks to prioritize learning low frequency functions - is one possible...

Gathering training data is a key step of any supervised learning task, and it is both critical and expensive. Critical, because the quantity and quality of the training data has a high impact on the performance of the learned function. Expensive, because most practical cases rely on humans-in-the...

It is well known that vision classification models suffer from poor calibration in the face of data distribution shifts. In this paper, we take a geometric approach to this problem. We propose Geometric Sensitivity Decomposition (GSD) which decomposes the norm of a sample feature embedding and the...

Before we reach model training in the pipeline, there are various components like data ingestion, data versioning, data validation, and data pre-processing that need to be executed. In this article, we will discuss data validation, why it is important, its challenges, and more.

A new method forces a machine learning model to focus on more data when learning a task, which leads to more reliable predictions.

Learning optimal policies in sparse rewards settings is difficult as the learning agent has little to no feedback on the quality of its actions. In these situations, a good strategy is to focus on exploration, hopefully leading to the discovery of a reward signal to improve on. A learning algorithm...

Video salient object detection aims to find the most visually distinctive objects in a video. To explore the temporal dependencies, existing methods usually resort to recurrent neural networks or optical flow. However, these approaches require high computational cost, and tend to accumulate...

Despite being able to capture a range of features of the data, high accuracy models trained with supervision tend to make similar predictions. This seemingly implies that high-performing models share similar biases regardless of training methodology, which would limit ensembling benefits and render...

Ultrasound (US) imaging is commonly used to assist in the diagnosis and interventions of spine diseases, while the standardized US acquisitions performed by manually operating the probe require substantial experience and training of sonographers. In this work, we propose a novel dual-agent framework...

Check out this guide to implementing different types of encoding for categorical data, including a cheat sheet on when to use what type.

Unis are using artificial intelligence to keep students sitting exams honest. But this creates its own problems

We address the problem of goal-directed cloth manipulation, a challenging task due to the deformability of cloth. Our insight is that optical flow, a technique normally used for motion estimation in video, can also provide an effective representation for corresponding cloth poses across observation...

We have recently introduced a system that automatically generates robotic planning operators from human demonstrations. One feature of our system is the operator count, which keeps track of the application frequency of every operator within the demonstrations. In this extended abstract, we show that...

This paper presents a hierarchical segment-based optimization method for Simultaneous Localization and Mapping (SLAM) system. First we propose a reliable trajectory segmentation method that can be used to increase efficiency in the back-end optimization. Then we propose a buffer mechanism for the...

Much of the existing linguistic data in many languages of the world is locked away in non-digitized books and documents. Optical character recognition (OCR) can be used to produce digitized text, and previous work has demonstrated the utility of neural post-correction methods that improve the...

You have heard it before, and you will hear it again. It's all about the data. Curating the right data is also so important than just curating any data. When dealing with text data, many hard-earned lessons have been learned by others over the years, and here are four data curation tips that you...