In this paper, the effects of nonsingular affine transforms on various nonlinear network training algorithms are analyzed. It is shown that gradient related methods, are quite sensitive to an input affine transform, while Newton related methods are invariant. These results give a connection between pre-processing techniques and weight initialization methods. They also explain the advantages of ...

Despite the success of deep neural networks (DNNs) for real-world applications over time-series data such as mobile health, little is known about how to train robust DNNs domain due its unique characteristics compared images and text data. In this paper, we fill gap by proposing a novel algorithmic framework referred RObust Training Time-Series (RO-TS) create models classification tasks. Specif...

Abstract X-ray computed tomography (CT) is a powerful technique for non-destructive volumetric inspection of objects and widely used studying internal structures large variety sample types. The raw data obtained through an CT practice gray-scale 3D array voxels. This must undergo geometric feature extraction process before it can be interpretation purposes. Such conventionally done manually, bu...

In recent years, the increasing demand for physical health promotes basketball sports industry’s reform. The latest science and technology enter industry one after another constantly impact traditional equipment. However, conventional scheme is unreasonable, training management models are obsolete. So, it impossible to use scientific methods in training, overall effect not good. This paper prop...

The training process for deep learning and pattern recognition normally involves the use of convex strongly optimization algorithms such as AdaBelief SAdam to handle lots “uninformative” samples that should be ignored, thus incurring extra calculations. To solve this open problem, we propose design bandit sampling method make these focus on “informative” during process. Our contribution is twof...

Evolutionary neural architecture search (ENAS) can automatically design the architectures of deep networks (DNNs) using evolutionary computation algorithms. However, most ENAS algorithms require an intensive computational resource, which is not necessarily available to users interested. Performance predictors are a type regression models assist accomplish search, while without exerting much res...