Abstract: Described herein is a machine learning mechanism implemented by one or more computers, the mechanism having access to a base neural network and being configured to determine a simplified neural network by iteratively performing the following set of steps: forming sample data by sampling the architecture of a current candidate neural network; selecting, in dependence on the sample data, an architecture for a second candidate neural network; forming a trained candidate neural network by training the second candidate neural network, wherein the training of the second candidate neural network comprises applying feedback to the second candidate neural network in dependence on a comparison of the behaviours of the second candidate neural network and the base neural network; and adopting the trained candidate neural network as the current candidate neural network for a subsequent iteration of the set of steps.

Abstract: A device for machine learning is provided, including a first neural network layer, a second neural network layer with a normalization layer arranged in between. The normalization layer is configured to, when the device is undergoing training on a batch of training samples, receive multiple outputs of the first neural network layer for a plurality of training samples of the batch, each output comprising multiple data values for different indices on a first dimension and a second dimension; group the outputs into multiple groups based on the indices on the first and second dimensions; form a normalization output for each group which are provided as input to the second neural network layer. According to the application, the training of a deep convolutional neural network with good performance that performs stably at different batch sizes and is generalizable to multiple vision tasks is achieved, thereby improving the performance of the training.

Abstract: The invention relates to the technical field of screen protection, and in particular, relates to a screen cover piece, acting as a filter, of specific colors that will filter the bright light and bright glare emitted from the viewing screens of various electronic devices. A transparent color screen filter cover will be made of polyethylene terephthalate (PET) film, polyurethane film, and/or tempered glass with the composition of an Anti-Glare layer and a Hard Coating Layer. A gluing layer is applied on any side of the piece body or no gluing layer may be applied for other utility options. The transparent colored light filtering screen cover besides filtering out the irritating, bright light from electronic devices is also an aesthetically enhancing screen cover piece for such devices. The color spectrums being claimed for such transparent color tinted screen filter covers are: orange, red, rose, yellow, gold, green, brown, amber, copper and/or purple.