Feature scaling is a method to unify self-variables or feature ranges in data. In data processing, it is usually used in data pre-processing. Because in the original data, the range of variables is very different. Feature scaling is a necessary step in the calculation of stochastic gradient descent. This paper takes the computer hardware data set maintained by UCI as an example, and compares the influence of normalization method and interval scaling method on the convergence of stochastic gradient descent by algorithm simulation. The result of study has a certain value on feature scaling.

Text-based CAPTCHAs remain the most widely adopted security scheme, which is the first barrier to securing websites. Deep learning methods, especially Convolutional Neural Networks (CNNs), are the mainstream approach for text CAPTCHA recognition and are widely used in CAPTCHA vulnerability assessment and data collection. However, verification code recognizers are mostly deployed on the CPU platform as part of a web crawler and security assessment; they are required to have both low complexity and high recognition accuracy. Due to the specifically designed anti-attack mechanisms like noise, interference, geometric deformation, twisting, rotation, and character adhesion in text CAPTCHAs, some characters are difficult to efficiently identify with high accuracy in these complex CAPTCHA images. This paper proposed a recognition model named Adaptive CAPTCHA with a CNN combined with an RNN (CRNN) module and trainable Adaptive Fusion Filtering Networks (AFFN), which effectively handle the interference and learn the correlation between characters in CAPTCHAs to enhance recognition accuracy. Experimental results on two datasets of different complexities show that, compared with the baseline model Deep CAPTCHA, the number of parameters of our proposed model is reduced by about 70%, and the recognition accuracy is improved by more than 10 percentage points in the two datasets. In addition, the proposed model has a faster training convergence speed. Compared with several of the latest models, the model proposed by the study also has better comprehensive performance.

In machine learning problems, there are two main algorithms: supervised learning and unsupervised learning. Supervised learning algorithms can be used to classify data for tagged data; non-supervised learning algorithms can be used to cluster data for unlabeled data. This paper discusses the basic principles of clustering algorithm and selection of key parameters of clustering algorithm. The application of clustering algorithm in image compression is also analyzed. This paper also emphasizes the problems that should be paid attention to when using clustering. Finally, a practical case of image compression with K-means is given.

Polynomial regression can be used for nonlinear models. When solving polynomial regression problems, polynomial regression can be transformed into linear regression to solve. In order to avoid over-fitting in polynomial regression, a regularization method can be used to suppress the coefficients of higher-order polynomial, and the article evaluates the influence of regularization coefficients on polynomial regression.

The security of cyberspace has become a global common concern, with websites and information systems facing significant threats. Text-based CAPTCHAs, widely implemented by websites, play a crucial role in preventing illicit attacks by robots and crawlers. However, in recent years, various breaking methods, particularly those based on deep learning, have emerged. This paper conducts a comprehensive investigation into the resistance mechanisms of text-based CAPTCHAs, analyzing their technical aspects in CAPTCHA design. Subsequently, we explore the recognition procedures of CAPTCHA utilizing deep learning models and compare representative algorithms developed in recent years. Finally, we evaluate the positives and negatives of different cracking algorithms and summarize our findings.