CALIFORNIA SCIENCE AND TECHNOLOGY UNIVERSITY

Home Browse Search

CS04 ;„;_it1I ."ping Fundamentat(1 5 units)'; The Machine Learning course provides students with the ability to apply machine learning or predictive analytics methods. Machine learning models covered include classifiers, regression and unsupervised learning. Some more advanced topics, such as, deep learning models are introduced. In this course, you will learn how to apply machine learning to creating data driven solutions to business problems, query data sources for both training machine learning models and production models. You will also learn how to construct, evaluate, and cross -validate classification and regression models to predict value in production and how to construct unsupervised learning models to discover and understand structure in unlabeled data sets, develop and understand deep learning models and their relationship to other machine learning models. CSE606'AI IApplication with GAN (1.5 units) This course focuses on deep neural network learning with Generative Adversarial Network (GAN) and introduces some key concepts in deep neural learning. Training Deep learning networks requires a good understanding of the nature of gradient descent and its variant, and different forms of loss functions. GAN is a class of machine learning frameworks. Given a training set, GAN learns to generate new data with the same statistics as the training set. A GAN trained on photographs can generate new photographs that look at least superficially authentic to human observers. Though originally proposed as a form of generative model for unsupervised learning, GANs have also proven useful for semi -supervised learning, fully supervised learning, and reinforcement learning. The core idea of a GAN is based on the "indirect" training through the discriminator, which itself is also being updated dynamically. 60$ AI Application with RemforcementRLearning (1.5;rnits) This course focuses on in-depth understanding of deep learning applications and introduces some key concepts in reinforcement learning. Training Deep learning networks can be a challenging task and requires a good understanding of the nature of gradient descent and its variants. Students will learn about different forms of loss functions and hyper parameters and regularization in conv nets, RNNs and others. The focus then turns into reinforcement learning as an alternative to supervised learning, OpenAI Gym is introduced as a tool to simulate the agent's environment and interaction. We will use Keras as a key framework to model different neural network architectures. Owk loud Computing and Security', ja-.5 units) This course offers students an in-depth understanding and hands-on experience of cloud computing using AWS. It will cover a wide range of topics in Compute, Storage, Networking, Security, Monitoring and Logging, as well as Account and Cost Management. Topics include evolution of cloud computing, AWS global infrastructure, architectural principles, key services Page 56 of 65