Recent studies have indicated that foundation models, such as BERT and GPT, excel in adapting to a variety of downstream tasks.
Existing model evaluation tools mainly focus on evaluating classification models, leaving a gap in evaluating more complex models, such as object detection.
When exploring time series datasets, analysts often pose "which and when" questions.
To ease this process, we develop ArchExplorer, a visual analysis method for understanding a neural architecture space and summarizing design principles.
The rapid development of deep natural language processing (NLP) models for text classification has led to an urgent need for a unified understanding of these models proposed individually.
The base learners and labeled samples (shots) in an ensemble few-shot classifier greatly affect the model performance.
In contrast to previous work, our system also works with non-geolocated posts and avoids extensive preprocessing such as detecting events.
The novelty of our approach includes 1) automatically constructing constraints for hierarchical clustering using knowledge (knowledge-driven) and intrinsic data distribution (data-driven), and 2) enabling the interactive steering of clustering through a visual interface (user-driven).
The growing use of automated decision-making in critical applications, such as crime prediction and college admission, has raised questions about fairness in machine learning.
Concept drift is a phenomenon in which the distribution of a data stream changes over time in unforeseen ways, causing prediction models built on historical data to become inaccurate.
To better analyze and understand the OoD samples in context, we have developed a novel kNN-based grid layout algorithm motivated by Hall's theorem.
Interactive Machine Learning (IML) is an iterative learning process that tightly couples a human with a machine learner, which is widely used by researchers and practitioners to effectively solve a wide variety of real-world application problems.
Recently, deep learning has been advancing the state of the art in artificial intelligence to a new level, and humans rely on artificial intelligence techniques more than ever.
Finally, we propose an efficient distributed implementation of PCGS through vectorization, pre-processing, and a careful design of the concurrent data structures and communication strategy.
Interactive model analysis, the process of understanding, diagnosing, and refining a machine learning model with the help of interactive visualization, is very important for users to efficiently solve real-world artificial intelligence and data mining problems.
Deep convolutional neural networks (CNNs) have achieved breakthrough performance in many pattern recognition tasks such as image classification.
To facilitate users in analyzing the flow, we present a method to model the flow behaviors that aims at identifying the lead-lag relationships between word clusters of different user groups.