Low-rank matrices play a fundamental role in modeling and computational methods for
signal processing and machine learning. In many applications where low-rank matrices …

Introduction: Neural networks are becoming a very popular method for solving machine
learning and artificial intelligence problems. The variety of neural network types and their …

With a goal of understanding what drives generalization in deep networks, we consider
several recently suggested explanations, including norm-based control, sharpness and …

This paper studies few-shot learning via representation learning, where one uses $ T $
source tasks with $ n_1 $ data per task to learn a representation in order to reduce the …

We present weight normalization: a reparameterization of the weight vectors in a neural
network that decouples the length of those weight vectors from their direction. By …

Kwang Gi Kim https://doi. org/10.4258/hir. 2016.22. 4.351 ing those who are beginning their
careers in deep learning and artificial intelligence research. The other target audience …

Deep learning based on artificial neural networks is a very popular approach to modeling,
classifying, and recognizing complex data such as images, speech, and text. The …

We study implicit regularization when optimizing an underdetermined quadratic objective
over a matrix $ X $ with gradient descent on a factorization of X. We conjecture and provide …

Matrix completion is a basic machine learning problem that has wide applications,
especially in collaborative filtering and recommender systems. Simple non-convex …

In inductive transfer learning, fine-tuning pre-trained convolutional networks substantially
outperforms training from scratch. When using fine-tuning, the underlying assumption is that …