Deep Learning (DL) is a pivotal skill in artificial intelligence, renowned for its applications in achieving state-of-the-art results in various tasks within Computer Vision and Natural Language Processing (NLP). This course offers an in-depth exploration of DL foundations, enabling students to build, train, and implement neural networks effectively and efficiently. In this course, students will learn various neural network architectures, understand how to optimize network performance and apply deep learning to solve complex problems in NLP and computer vision. This course will cover MLP neural networks, Sequence modeling techniques (RNN, LSTM, seq2seq etc.), attention mechanism, encoder-decoder architecture, convolutional neural networks, Adversarial neural networks, transfer learning, as well as some topics that are necessary for successful network training such as optimization methods (SGD, momentum, Adam), dropout, batch normalization, model selection and model evaluation. The course will also introduce the students to some NLP and computer vision tasks using deep learning. The final project will involve developing and training a deep neural network model and applying it to an interesting problem.