Neural Networks

Neural Networks is a project-based graduate course aimed to provide practical and fundamental skills to perform scholarly work with neural networks.

The course will survey the fundamentals of learning in Artificial Neural Networks (ANN) and describe the underlying principles making neural networks common computing contexts. Furthermore, developing computational skills for training neural networks, understanding, and working with algorithms such as backpropagation, gradient descent and different types of ANNs, such as Convolutional networks and Recurrent NNs. The course will culminate with projects developing ANN systems to provide efficient solutions to applications.

 

Throughout the semester, synchronous teaching using webex, zoom or google meet will be used which will bring back the engaging dynamic of the classroom. Asynchronous teaching strategy will also be used using this (MOODLE) software platform. Since this platform is limited to 2MB capacity per file upload, google drive will be utilized for students to access the course materials. To achieve a high quality of information transfer, audio and visual channels are applied. The course type includes lecture, discussion-based seminar and laboratory. Active learning and group or individual work on classification and clustering problems using artificial neural network techniques and tools.