Breast cancer ranks highest among female cancers in terms of both prevalence and mortality. Background: Breast cancer is a global health problem affecting females. Breast cancer is the most commonly reported cancer type among women globally, with 2.3 million new cases diagnosed each year, according to World Health Organization data. However, breast cancer is also quite deadly, which makes it a serious problem for patients and healthcare providers—as well as policymakers. As a result, the implications of this study, as they may relate to early and accurate breast cancer detection, providing for improved patient outcomes, should be significant. In this study, we introduce a model to identify breast cancer from histopathological images based on deep convolutional neural networks (CNN). The deep CNN model (transfer learning) is used in conjunction with several classifiers, for example, SVM, Decision Tree, and KNN. Experiments were performed with two different feature vectors, PCA and its absence. The performance of the proposed model is compared with deep learning models based on false positive rate, true positive rate, accuracy, precision, and recall values [30]. Based on the results, it can be concluded that the SVM algorithm using PCA features output is relatively the fastest, producing an accuracy of 99.5% while based on the highest accuracy ranking Decision Tree without applying PCA produces an accuracy of 99.4%.