Abstract: A neuron-level plasticity control (NPC) addresses the issue of catastrophic forgetting in an artificial neural network. The plasticity of a network is controlled at a neuron level rather than at a connection level during training of a new task, thereby conserving existing knowledge. The neuron-level plasticity control evaluates the importance of each neuron and applies a low training speed to integrate important neurons. In addition, a scheduled NPC (SNPC) is provided that uses training schedule information to more clearly protect important neurons.

Abstract: The present disclosure pertains to a board connector comprising a plurality of radio frequency (RF) contacts for transmitting RF signals; an insulating part supporting the RF contacts; a plurality of transmission contacts coupled to the insulating part and between a first RF contact and a second RF contact, such that the first RF contact and the second RF contact are spaced in a first axial direction; and a grounding housing to which the insulating part is coupled, the grounding housing comprising an inner grounding wall, an outer grounding wall spaced apart from the inner grounding wall, and a grounding connection wall coupled to each of the inner and outer grounding walls, wherein the inner and outer grounding walls are double-shielding walls that surround the side of an inner space, and the first RF contact and the second RF contact are placed in the inner space surrounded by the double-shielding walls.

Abstract: Disclosed are a volume adjusting device and an adjusting method thereof for enabling an electronic device such as a TV to perform a volume adjustment operation among operations executable by the electronic device according to a prediction model stored through machine learning based on communication with surrounding devices in a 5G communication environment. According to the present disclosure, when information indicating adjustment of the volume of an electronic device by a user is generated, volume adjustment information may be learned, and the volume may be automatically adjusted to a volume preferred by the user on the basis of the learned information when the user views a video on the electronic device.

Abstract: Disclosed are a volume adjusting device and an adjusting method thereof for enabling an electronic device such as a TV to perform a volume adjustment operation among operations executable by the electronic device according to a prediction model stored through machine learning based on communication with surrounding devices in a 5G communication environment. According to the present disclosure, when information indicating adjustment of the volume of an electronic device by a user is generated, volume adjustment information may be learned, and the volume may be automatically adjusted to a volume preferred by the user on the basis of the learned information when the user views a video on the electronic device.

Abstract: An apparatus for bonding substrates and a method of bonding substrates are provided. In accordance with one exemplary embodiment of the present invention, a first plate to mount a first substrate is provided. A chamber body movably connected to the first plate is provided. A second plate that is placed opposite to the first plate and a second substrate is mounted on the second plate is provided. A chamber lead having the second plate mounted inside is provided which is movably connected to the chamber body to move rotationally or linearly to open or close the chamber space with the chamber body. A pair of first alignment cameras is placed outside of the chamber space to scan the first substrate or the second substrate. A stage control unit is provided to move the first plate or the second plate to align the first substrate and the second substrate.