Machine Learning and Knowledge Discovery

This course will provide you a foundational understanding of machine learning models as well as demonstrate how these models can solve complex problems in a variety of fields. Topics include:  (i) Supervised learning (neural networks, support vector machines, kernels, hidden markov models). (ii) Unsupervised learning (clustering, dimensionality reduction, autoencoder, Bert, simCLR). (iii) Deep learning (convolutional neural network, recurrent and recursive neural network, generative adversarial network, transfer learning, transformer ). The course will also draw from numerous case studies and applications, so that you'll also learn how to apply learning algorithms to building smart robots, text understanding, computer vision, database mining, and other areas. In addition, we have designed practice exercises that give you hands-on experience implementing these data science models on data sets. These practice exercises will teach you how to implement machine learning algorithms with PyTorch, open source libraries in the machine learning fields.