Abstract: In this study, we deal with the question of diagnosing brain bleeding that radiologists consider a laborious procedure, particularly in the early stages of bleeding. The challenge is resolved with a deep learning strategy in which a convolutions neural network and well-known neural network (CNN) are trained to categorise brain computer tomography (CT) images into haemorrhage or nonhemorrhage images. Alexnet also has a modified new version (Alex Net-SVM). In medical image analytics and classification the objective of using the model of deep learning is to answer the key problem: can the requirement to develop CNN be removed by a suitable smoothing of a pre-trained model (transfer learning)? In addition, this study will also explore the benefits of employing SVM as a classifier rather than a three-layer neural network. We utilise the identical classification task in three deep networks; one is developed from scratch and the other is a pretrained model that was fine tuneed to the brain CT haemorrhage classification task. The three networks have been trained with the same number of CT brain pictures. The investigations show that it is possible to transfer information from natural photos to the classification of medical images. Moreover, our findings have shown that the proposed modified “AlexNet-SVM” model may be used to identify the brain bleeding through an overall neural network developed from scratch, and by the original AlexNet.