Breast cancer plays a major role in mortality rates among women. Timely identification of breast cancer reduces the death rate linked to the illness. For early detection of the disease, conventional methods are used in the form of manual inspection. But these methods are prone to human errors and time-consuming too. Nowadays with the advent of various artificial intelligence techniques in the field of healthcare, various techniques are evolved for timely diagnosis of breast cancer. Computer-Aided Diagnosis (CAD) using Convolutional Neural Network (CNN) has recently been utilized to address the fatigue and reduced focus that histopathologists and physicians have when diagnosing cancer. Models based on convolutional neural networks (CNNs) have shown impressive outcomes in classifying breast histopathology images. This article presents a CNN which is evaluated on BreakHis dataset of Histopathology images. The proposed approach attained an average accuracy rate of 98% with 70–30% train-test split, 98% with 80–20% train-test split, and 99% with 90–10% train-test split in classifying the image dataset. This result provides proof of the effectiveness of advanced learning approaches in improving the speed and accuracy of classifying Histopathology images.