Abstract: The disclosed technology provides methods for training of a convolutional neural network (CNN) to identify or predict its own errors, and then those errors are used as inputs with feature visualization to generate images of scenes associated with those errors. This allows adjustment of a set of labeled training images, and then the adjusted set of labeled training images are used to retrain or further train the CNN. Systems and machine-readable media are also provided.

Abstract: The disclosed technology provides solutions for finding samples from image data that are similar to failure cases, by constructing N-dimensional vectors of the failure cases. The vectors of failure cases are compared to other image data, with the objective of identifying groups of images that can be labeled. The labeled images are then used to retrain a model. Systems and machine-readable media are also provided.

Abstract: A nonenzymatic biosensor based on a metal-modified porous boron-doped diamond electrode, and a method for preparing the same and use thereof are provided. A working electrode of the nonenzymatic biosensor is a metal-modified porous boron-doped diamond electrode including a silicon wafer substrate and an electrode working layer arranged on a surface thereof, the electrode working layer is a porous boron-doped diamond layer modified with metal nanoparticles, and a pore surface of the porous boron-doped diamond layer contains an sp2 phase. In the present invention, by combining chemical vapor deposition and magnetron sputtering and by means of a tubular atmosphere annealing furnace and an electrochemical workstation, the preparation of a multi-metal-modified porous boron-doped diamond composite electrode is realized.