Invention Grant
- Patent Title: Multi-modal neural network for universal, online learning
-
Application No.: US15456429Application Date: 2017-03-10
-
Publication No.: US10282661B2Publication Date: 2019-05-07
- Inventor: Dharmendra S. Modha
- Applicant: International Business Machines Corporation
- Applicant Address: US NY Armonk
- Assignee: International Business Machines Corporation
- Current Assignee: International Business Machines Corporation
- Current Assignee Address: US NY Armonk
- Agency: Sherman IP LLP
- Agent Kenneth L. Sherman; Hemavathy Perumal
- Main IPC: G06N3/02
- IPC: G06N3/02 ; G06N3/08 ; G06N3/04

Abstract:
In one embodiment, the present invention provides a neural network comprising multiple modalities. Each modality comprises multiple neurons. The neural network further comprises an interconnection lattice for cross-associating signaling between the neurons in different modalities. The interconnection lattice includes a plurality of perception neuron populations along a number of bottom-up signaling pathways, and a plurality of action neuron populations along a number of top-down signaling pathways. Each perception neuron along a bottom-up signaling pathway has a corresponding action neuron along a reciprocal top-down signaling pathway. An input neuron population configured to receive sensory input drives perception neurons along a number of bottom-up signaling pathways. A first set of perception neurons along bottom-up signaling pathways drive a first set of action neurons along top-down signaling pathways. Action neurons along a number of top-down signaling pathways drive an output neuron population configured to generate motor output.
Public/Granted literature
- US20170185896A1 MULTI-MODAL NEURAL NETWORK FOR UNIVERSAL, ONLINE LEARNING Public/Granted day:2017-06-29
Information query