Title:
EFFICIENTLY BUILDING DEEP NEURAL NETWORKS
Document Type and Number:
WIPO Patent Application WO/2020/041026
Kind Code:
A8
Abstract:
A computer system uses a pool of predefined functions and pre-trained networks to accelerate the process of building a large neural network or building a combination of (i) an ensemble of other machine learning systems with (ii) a deep neural network. Copies of a predefined function node or network may be placed in multiple locations in a network being built. In building a neural network using a pool of predefined networks, the computer system only needs to decide the relative location of each copy of a predefined network or function. The location may be determined by (i) the connections to a predefined network from source nodes and (ii) the connections from a predefined network to nodes in an upper network. The computer system may perform an iterative process of selecting trial locations for connecting arcs and evaluating the connections to choose the best ones.
Inventors:
BAKER JAMES (US)
Application Number:
PCT/US2019/046178
Publication Date:
August 27, 2020
Filing Date:
August 12, 2019
Export Citation:
Assignee:
D5AI LLC (US)
International Classes:
G06N3/02; G06N3/04; G06N3/063; G06N3/08
Attorney, Agent or Firm:
KNEDEISEN, Mark et al. (US)
Download PDF: