Despite recent advances in the field of explainability, much remains unk...
Recent years have witnessed an explosion in the development of novel
pre...
The meteoric rise in the adoption of deep neural networks as computation...
Feature visualization has gained substantial popularity, particularly af...
In recent years, concept-based approaches have emerged as some of the mo...
One of the most impactful findings in computational neuroscience over th...
Deep neural networks (DNNs) are known to have a fundamental sensitivity ...
Research in Machine Learning has polarized into two general regression
a...
An important milestone for AI is the development of algorithms that can
...
Many tasks can be described as compositions over subroutines. Though mod...
Attribution methods are a popular class of explainability methods that u...
The many successes of deep neural networks (DNNs) over the past decade h...
Vision transformers are nowadays the de-facto preference for image
class...
A fundamental component of human vision is our ability to parse complex
...
Humans continue to outperform modern AI systems in their ability to flex...
Today's most advanced machine-learning models are hardly scrutable. The ...
Robust generalization to new concepts has long remained a distinctive fe...
A variety of methods have been proposed to try to explain how deep neura...
Recent meta-reinforcement learning work has emphasized the importance of...
A multitude of explainability methods and theoretical evaluation scores ...
We describe a novel attribution method which is grounded in Sensitivity
...
Nearly all models for object tracking with artificial neural networks de...
Visual understanding requires comprehending complex visual relations bet...
Imagine trying to track one particular fruitfly in a swarm of hundreds.
...
Networks of coupled oscillators are some of the most studied objects in ...
Our ability to generalize beyond training data to novel, out-of-distribu...
We introduce a deep recurrent neural network architecture that approxima...
The intriguing connections recently established between neural networks ...
Primate vision depends on recurrent processing for reliable perception
(...
Forming perceptual groups and individuating objects in visual scenes is ...
Recent successes in deep learning have started to impact neuroscience. O...
We present a novel approach for estimating the 2D pose of an articulated...
State-of-the-art deep convolutional networks (DCNs) such as squeeze-and-...
Progress in deep learning has spawned great successes in many engineerin...
The robust and efficient recognition of visual relations in images is a
...
Although Deep Convolutional Networks (DCNs) are approaching the accuracy...
Rapid categorization paradigms have a long history in experimental
psych...
We describe an end-to-end generative approach for the segmentation and
r...
Deep learning has recently led to great successes in tasks such as image...