Boris Knyazev of the University of Guelph in Ontario and his colleagues have designed and trained a "hypernetwork" that could speed up the training of neural networks. Given a new, untrained deep neural network designed for some task, the hypernetwork predicts the parameters for the new network in fractions of a second, and in theory could make training unnecessary. The work may also have deeper theoretical implications.
The name outlines the approach. "Graph" refers to the idea that the architecture of a deep neural network can be thought of as a mathematical graph — a collection of points, or nodes, connected by lines, or edges. The nodes represent computational units (usually, an entire layer of a neural network), and edges represent the way these units are interconnected.
The approach is described in "Parameter Prediction for Unseen Deep Architectures."
From Quanta Magazine
View Full Article
No entries found