Search Results for author:
Found 11 papers, 6 papers with code
No News is Good News: A Critique of the One Billion Word Benchmark
The One Billion Word Benchmark is a dataset derived from the WMT 2011 News Crawl, commonly used to measure language modeling ability in natural language processing.
Mitigating harm in language models with conditional-likelihood filtration
Language models trained on large-scale unfiltered datasets curated from the open web acquire systemic biases, prejudices, and harmful views from their training data.
Neural Additive Models: Interpretable Machine Learning with Neural Nets
They perform similarly to existing state-of-the-art generalized additive models in accuracy, but are more flexible because they are based on neural nets instead of boosted trees.
Deflecting Adversarial Attacks
There has been an ongoing cycle where stronger defenses against adversarial attacks are subsequently broken by a more advanced defense-aware attack.
Detecting and Diagnosing Adversarial Images with Class-Conditional Capsule Reconstructions
Then, we diagnose the adversarial examples for CapsNets and find that the success of the reconstructive attack is highly related to the visual similarity between the source and target class.
Analyzing and Improving Representations with the Soft Nearest Neighbor Loss
We explore and expand the $\textit{Soft Nearest Neighbor Loss}$ to measure the $\textit{entanglement}$ of class manifolds in representation space: i. e., how close pairs of points from the same class are relative to pairs of points from different classes.
SMILER: Saliency Model Implementation Library for Experimental Research
The Saliency Model Implementation Library for Experimental Research (SMILER) is a new software package which provides an open, standardized, and extensible framework for maintaining and executing computational saliency models.
DARCCC: Detecting Adversaries by Reconstruction from Class Conditional Capsules
In addition to being trained to classify images, the capsule model is trained to reconstruct the images from the pose parameters and identity of the correct top-level capsule.
Matrix capsules with EM routing
A capsule in one layer votes for the pose matrix of many different capsules in the layer above by multiplying its own pose matrix by trainable viewpoint-invariant transformation matrices that could learn to represent part-whole relationships.
Ranked #4 on
Image Classification
on smallNORB
Distilling a Neural Network Into a Soft Decision Tree
They excel when the input data is high dimensional, the relationship between the input and the output is complicated, and the number of labeled training examples is large.
Dynamic Routing Between Capsules
We use the length of the activity vector to represent the probability that the entity exists and its orientation to represent the instantiation parameters.
Ranked #1 on
Image Classification
on MultiMNIST
