This paper contributes a new machine learning solution for stock movement prediction, which aims to predict whether the price of a stock will be up or down in the near future. The key novelty is that we propose to employ adversarial training to improve the generalization of a neural network prediction model. The rationality of adversarial training here is that the input features to stock prediction are typically based on stock price, which is essentially a stochastic variable and continuously changed with time by nature. As such, normal training with static price-based features (e.g., the close price) can easily overfit the data, being insufficient to obtain reliable models. To address this problem, we propose to add perturbations to simulate the stochasticity of price variable, and train the model to work well under small yet intentional perturbations. Extensive experiments on two real-world stock data show that our method outperforms the state-of-the-art solution [Xu and Cohen, 2018] with 3.11% relative improvements on average w.r.t. accuracy, validating the usefulness of adversarial training for stock prediction task.

No abstract

No abstract

One key issue in the optical measurement of free-form or complex surfaces is the point cloud registration procedure, which aligns the measurement data to the part model for a robust, fast and accurate inspection process. Therefore, a robust registration method for surface inspection is proposed based on an adaptive distance function (ADF) and the M-estimation method. The ADF as the basis error metric can accurately describe the shortest point-surface distance, and the M-estimation method is used to eliminate outliers and enhance the robustness of the registration performance. The registration problem using the M-estimation method can be interpreted as an iterative reweighted least squares (IRLS) minimization. Then, a nonlinear optimization model called IRLS-ADF is established to obtain the transformation parameters. The convergence of the proposed method is also analysed. Moreover, compared to the previous algorithms, the experiments confirm that the proposed method can achieve a combination of good robustness, fast convergence speed and high accuracy.

No abstract