Abstract: An access point device operable in a wireless network detects multi-band capability of a wireless client based on a probe request received from the wireless client on the non-preferred communication band. The multi-band capability is detected based on a set of parameters included in the received probe request. When the wireless client is detected to have the multi-band capability, the access point device blocks the attempt of the first wireless client to associate on the non-preferred communication band. The access point device allows the wireless client to associate on one of the non-preferred communication band and a preferred communication band based on a count of probe requests received by the access point device from the wireless client on the non-preferred communication band. Upon association on the non-preferred communication band, the access point device steers the associated wireless client to the preferred communication band.

Abstract: Embodiments of the present disclosure relate to generating explanation maps for explaining convolutional neural networks through attribution-based input sampling and block-wise feature aggregation. An example of a disclosed method for generating an explanation map for a convolutional neural network (CNN) includes obtaining an input image resulting in an output determination of the CNN, selecting a plurality of feature maps extracted from a plurality of pooling layers of the CNN, generating a plurality of attribution masks based on the plurality of feature maps, applying the generated attribution masks to the input image to obtain a plurality of visualization maps, and generating an explanation map of the output determination of the CNN based on the plurality of visualization maps.

Abstract: Embodiments of the present disclosure relate to generating explanation maps for explaining convolutional neural networks through attribution-based input sampling and block-wise feature aggregation. An example of a disclosed method for generating an explanation map for a convolutional neural network (CNN) includes obtaining an input image resulting in an output determination of the CNN, selecting a plurality of feature maps extracted from a plurality of pooling layers of the CNN, generating a plurality of attribution masks based on the plurality of feature maps, applying the generated attribution masks to the input image to obtain a plurality of visualization maps, and generating an explanation map of the output determination of the CNN based on the plurality of visualization maps.

Abstract: A liquid composition is provided. The composition includes at least one active pharmaceutical ingredient dissolved in a liquid carrier system. The liquid carrier includes polyethylene glycol and a co-solvent selected from the group consisting of: propylene glycol, glycerin, and a sugar alcohol. The composition is essentially dye tree, present as a single-phase at room temperature, and optionally contains water.