Researchers are defining new types of interactions between humans and machine learning
algorithms generically called human-in-the-loop machine learning. Depending on who is in …

Rapid development of artificial intelligence motivates researchers to expand the capabilities
of intelligent and autonomous robots. In many robotic applications, robots are required to …

Making the Black Box More Transparent: Understanding the Physical Implications of Machine
Learning in: Bulletin of the American Meteorological Society Volume 100 Issue 11 (2019) Jump …

Existing image classification datasets used in computer vision tend to have a uniform
distribution of images across object categories. In contrast, the natural world is heavily …

We propose a technique for producing'visual explanations' for decisions from a large class
of Convolutional Neural Network (CNN)-based models, making them more transparent. Our …

We propose a technique for producing 'visual explanations' for decisions from a large class
of Convolutional Neural Network (CNN)-based models, making them more transparent and …

Transferring the knowledge learned from large scale datasets (eg, ImageNet) via fine-tuning
offers an effective solution for domain-specific fine-grained visual categorization (FGVC) …

Industrial automation effectively reduces the human effort in various activities of the industry.
In many autonomous systems, object recognition plays a vital role. Thus, finding a solution …

A multi-view image sequence provides a much richer capacity for object recognition than
from a single image. However, most existing solutions to multi-view recognition typically …

Modern systems can augment people's capabilities by using machine-learned models to
surface intelligent behaviors. Unfortunately, building these models remains challenging and …