AlexResNet+: Enhancing Breast Cancer Detection through Deep Learning Techniques

The area of machine learning that uses deep neural networks (DNNs) is called deep learning. Current developments in device learning with larger and deeper representation strategies are using a "cease-to-cease" instructional strategy, deep learning approaches and expand a deep learning set of protocols and methodologies that may accurately detect the majority of breast cancers during mammography screening. An efficient training method makes use of training datasets that either include the complete scientific annotation or only the most tumors found (tagged) throughout the image. According to deep learning, there are at least three or four layers, with the input layers leading to the output layers. A Deep Hybrid Featured Machine Learning Model for Classifying Breast Cancer Tissue is called AlexResNet+. We used the well-liked and incredibly successful deep learning models, AlexNet and ResNet101, for deep feature extraction. To achieve optimal computing efficiency while preserving high dimensional deep features, we employed AlexNet, which consists of three fully connected layers and five convolutional layers. In contrast, ResNet101 was used with modified layered structures. We combined the feature set and used it as input for the radial basis function support vector machine (SVM-RBF). which is employed in two-class classification, after extracting the distinctive deep features from the deep learning models of AlexNet and ResNet.To evaluate the effectiveness of the different feature sets, distinct performances for AlexNet, short for ResNet101, and hybrid features were obtained.