355 citations · 785 across the 20 of their papers we have counts for
20 papers
Linking convolutional kernel size to generalization bias in face analysis CNNs
Hao Liang, Josue Ortega Caro, Vikram Maheshri +2
Training dataset biases are by far the most scrutinized factors when explaining algorithmic biases of neural networks. In contrast, hyperparameters related to the neural network ar…
Understanding robustness and generalization of artificial neural networks through Fourier masks
Nikos Karantzas, Emma Besier, Josue Ortega Caro +4
Despite the enormous success of artificial neural networks (ANNs) in many disciplines, the characterization of their computations and the origin of key properties such as generaliz…
Bongard-LOGO: A New Benchmark for Human-Level Concept Learning and Reasoning
Weili Nie, Zhiding Yu, Lei Mao +3
Humans have an inherent ability to learn novel concepts from only a few samples and generalize these concepts to different situations. Even though today's machine learning models e…
Shallow Univariate ReLu Networks as Splines: Initialization, Loss Surface, Hessian, & Gradient Flow Dynamics
Justin Sahs, Ryan Pyle, Aneel Damaraju +4
Understanding the learning dynamics and inductive bias of neural networks (NNs) is hindered by the opacity of the relationship between NN parameters and the function represented. W…
An Improved Semi-Supervised VAE for Learning Disentangled Representations
Weili Nie, Zichao Wang, Ankit B. Patel +1
Learning interpretable and disentangled representations is a crucial yet challenging task in representation learning. In this work, we focus on semi-supervised disentanglement lear…
Local Convolutions Cause an Implicit Bias towards High Frequency Adversarial Examples
Josue Ortega Caro, Yilong Ju, Ryan Pyle +4
Adversarial Attacks are still a significant challenge for neural networks. Recent work has shown that adversarial perturbations typically contain high-frequency features, but the r…