This article presents a study on the state-of-the-art methods for automated radioactive materialdetection and identification, using gamma-ray spectra and modern machine learning methods. Therecent developments inspired this in deep learning algorithms, and the proposed method providedbetter performance than the current state-of-the-art models. Machine learning models such as: fullyconnected, recurrent, convolutional, and gradient boosted decision trees, are applied under a wide variety of testing conditions, and their advantage and disadvantage are discussed. Furthermore, a hybridmodel is developed by combining the fully-connected and convolutional neural network, which showsthe best performance among the different machine learning models. These improvements are represented by the model's test performance metric (i.e., F1 score) of 93.33% with an improvement of 2%e12%than the state-of-the-art model at various conditions. The experimental results show that fusion ofclassical neural networks and modern deep learning architecture is a suitable choice for interpretinggamma spectra data where real-time and remote detection is necessary