Time series forecasting is the process of predicting future values of a time series from
knowledge of its past data. Although there are several models for making short-term …

We perform an analysis of the average generalization dynamics of large neural networks
trained using gradient descent. We study the practically-relevant “high-dimensional” regime …

Skip connections made the training of very deep networks possible and have become an
indispensable component in a variety of neural architectures. A completely satisfactory …

This is the first comprehensive book on information geometry, written by the founder of the
field. It begins with an elementary introduction to dualistic geometry and proceeds to a wide …

This paper presents an active learning strategy for robotic systems that takes into account
task information, enables fast learning, and allows control to be readily synthesized by …

Batch Normalization (BN) has become an out-of-box technique to improve deep network
training. However, its effectiveness is limited for micro-batch training, ie, each GPU typically …

In this work, we reveal a strong implicit bias of stochastic gradient descent (SGD) that drives
overly expressive networks to much simpler subnetworks, thereby dramatically reducing the …

Sure to be influential, Watanabe's book lays the foundations for the use of algebraic
geometry in statistical learning theory. Many models/machines are singular: mixture models …

Gradient-based learning in multi-layer neural networks displays a number of striking
features. In particular, the decrease rate of empirical risk is non-monotone even after …

In this study, a transfer learning method was utilized to recognize and classify benign and
malignant breast tumors, using two-dimensional breast ultrasound (US) images, to decrease …