Archived Event - Deep Learning for Petroleum Engineers Using Python: Part 3 - Recurrent Neural Network, Autoencoders, Generative Adversarial Networks, and Transformer Models

The purpose of this course is to prepare the students to use Python programming to apply various deep learning algorithms to petroleum engineering problems. Participants will gain hands-on experience in Python programming and popular deep learning libraries such as TensorFlow and Keras. The course will cover essential concepts of deep learning, including neural networks, convolutional neural networks, recurrent neural networks, generative models, and reinforcement learning. The course will also present many recent examples for application of deep learning algorithms in petroleum engineering. Advancing into more specialized domains, Part 2 of the course introduces Convolutional Neural Networks (CNNs), a class of deep neural networks highly effective in processing visual imagery. Students learn about the architecture of CNNs, including convolutional layers, pooling, and flattening, and how these components enable the model to automatically and adaptively learn spatial hierarchies of features from input images. An integral part of this section is dedicated to Transfer Learning, where students learn to leverage pre-trained models to solve tasks with limited data, significantly reducing training time and computational cost. This section combines theoretical knowledge with practical applications, providing hands-on experience in image recognition and classification tasks.