Laserfiche WebLink
database backup/recovery methods. This course specifically details procedural extensions to <br />SQL to develop stored procedures, functions, packages and database triggers. In addition, it <br />covers database performance tuning from an application development point of view by exploring <br />query optimizer, database hints, and various database access methods. Cloud Database <br />Development and Management explains how student can take advantage of the cloud <br />environment to develop their own fully functioning database systems. <br />CSUM Machine Learning'(3 cred(ts) <br />This course will teach methods and techniques for using stored data to make decisions. The <br />student will learn data types including operational or transactional data such as data for sales, <br />cost, and inventory; nonoperational data such as forecast data and macroeconomic data; and meta <br />data, and learn their patterns, associations, or relationships, and how to use the information for <br />decision making. Statistical learning concepts such as regression, classification, decision trees <br />and model reduction techniques such as principal component analysis will be introduced. <br />Specific examples of engineering and businesses using data mining techniques will be given in <br />the course. The student is required to work on course projects by using modern data analysis <br />software and referring to cases studied. <br />l� " A,rf_ificiaLIptelligence Apphcdt on L(sl ig: Iensor:F,19w (3,credits) <br />This course will teach the fundamentals and contemporary usage of the TensorFlow library for <br />deep learning projects. The goal is to help students understand the graphical computational <br />model of TensorFlow, explore the functions it has to offer, and learn how to build and structure <br />models best suited for a deep learning project. The main content of the course includes the <br />following parts, TensorFlow basics, Linear and Logistic Regression and TensorFlow Serving, <br />Deep Neural Network, regularization, hyper -parameter tuning, Convolutional neural network, <br />LSTM and Seg2seq, and Reinforce Learning. Through the teaching, students will use <br />TensorFlow to build models of different complexity, from simple linear/logistic regression to <br />convolutional neural networks and recurrent neural networks to solve tasks such as word <br />embeddings, translation, optical character recognition. Students will also learn best practices to <br />structure a model and manage research experiments. <br />Deep Learning has become the most important skill in Al. This course will help students become <br />good at Deep Learning. In this course, students will learn the foundations of Deep Learning, <br />understand how to build neural networks, and learn how to apply machine learning knowledge in <br />real projects. The course will teach Convolutional networks, RNNs, LSTM, Adam, Dropout, <br />Batch Norm, and more. Students will work on projects from autonomous driving, sign reading, <br />and natural language processing. Students will master not only the theory, but also see how it is <br />applied in industry. Students will practice all these ideas in Python and in TensorFlow, which will <br />Page 54 of 65 <br />