Abstract: Methods and systems for budgeted and simplified training of deep neural networks (DNNs) are disclosed. In one example, a trainer is to train a DNN using a plurality of training sub-images derived from a down-sampled training image. A tester is to test the trained DNN using a plurality of testing sub-images derived from a down-sampled testing image. In another example, in a recurrent deep Q-network (RDQN) having a local attention mechanism located between a convolutional neural network (CNN) and a long-short time memory (LSTM), a plurality of feature maps are generated by the CNN from an input image. Hard-attention is applied by the local attention mechanism to the generated plurality of feature maps by selecting a subset of the generated feature maps. Soft attention is applied by the local attention mechanism to the selected subset of generated feature maps by providing weights to the selected subset of generated feature maps in obtaining weighted feature maps.

Abstract: An LED lamp with a windable filament and a process for making the same. The LED lamp includes a bulb shell, a support, an electrical connector and a driver. The support is externally connected to the bulb shell, and forms a vacuum sealed cavity with the bulb shell. The support is connected to a light bar through an electrical lead wire. The light bar placed in the vacuum sealed cavity is of a strip-shaped structure, and is provided with a substrate. A plurality of electrical connection circuits are uniformly arranged on the substrate. An LED chip is connected to the plurality of electrical connection circuits. A fluorescent colloid is provided on the substrate.