Abstract: A display device includes first and second electrodes, light-emitting elements on the first and second electrodes, data lines extending from a pad area to a display area, connection wirings spaced apart from the data lines and extending from the pad area to a non-display area on respective sides of the display area, first pads overlapping the data lines in the pad area, and second pads overlapping the connection wirings, wherein the connection wirings include a first connection wiring overlapping a second pad, a second connection wiring not overlapping the second pad and overlapping the first connection wiring in the non-display area, and a third connection wiring overlapping the first connection wiring and electrically connected to the second pad, wherein the first and third connection wirings overlap each other in the pad area, and the first, second, and third connection wirings overlap each other in the non-display area.

Abstract: Disclosed herein are a neural network model deployment method and apparatus for providing a deep learning service. The neural network model deployment method may include providing a specification wizard to a user, searching for and training a neural network based on a user requirement specification that is input through the specification wizard, generating a neural network template code based on the user requirement specification and the trained neural network, converting the trained neural network into a deployment neural network that is usable in a target device based on the user requirement specification, and deploying the deployment neural network to the target device.