 This paper proposes a novel deep learning algorithm for automatic modulation classification, AMC. The algorithm is based on residual learning and a squeeze and excite network, which are both inspired by the success of deep learning in other fields. The algorithm is able to achieve high accuracy while having significantly fewer parameters than existing convolutional neural networks. This makes it more efficient and suitable for real-time applications. The proposed model was tested on two benchmark datasets and compared with existing methods. The results showed that the proposed model outperformed existing methods in terms of accuracy and had up to 72.5% fewer parameters. This article was authored by Malik Sohaib Nisar, Muhammad Sohail Ibrahim, Muhammad Usman, and others.