XBUS-512 - Introduction to AI and Deep Learning

School of Continuing Studies

School of Continuing Studies

Disclaimer

Coursalytics is an independent platform to find, compare, and book executive courses. Coursalytics is not endorsed by, sponsored by, or otherwise affiliated with any business school or university.

Full disclaimer.

About the course

Of the many machine learning algorithms used today in industry and research, artificial neural models are quickly become the state of the art. For most of their ~70 year history, neural networks could not have been considered a practical machine learning method, but this has changed rapidly over the last two decades thanks to advances in distributed computing, optimizations in learning rates, and open source libraries like TensorFlow, Keras, and PyTorch. Perhaps even more importantly, unlike traditional models, which face performance plateaus as data size increases, neural models show particular promise because they continue to improve given more training data.

In this course we will use open source deep learning libraries to build machine learning models and develop practical strategies for prototyping, testing, visualizing, tuning, and deploying neural models to solve a range of real-world problems.

Enrollment in this course is open to all students and applies credit toward the

  • Data Science track or
  • Machine Learning track.

Course Objectives

Upon successful completion of the course, students will be able to:

  • Assess use cases in which AI and deep learning methods are well-suited.
  • Articulate tradeoffs between deep learning and traditional machine learning models.
  • Distinguish between experimental and production-ready AI and deep learning tools.
  • Prepare strategies for the deployment of deep neural models.
  • Leverage several deep learning libraries in Python such as TensorFlow, PyTorch, and Keras, able to appraise their affordances and limitations.
  • Compare and contrast the results of deep learning experiments across a wide search space of hyperparameter and network architecture choices.
  • Evaluate the effectiveness and efficacies of models using statistical methods.
  • Experiment with different deep learning architectures such as multilayer perceptrons, recurrent neural networks, and convolutional neural networks.

Experts

Rebecca Bilbro

Rebecca Bilbro is an adjunct faculty member in Georgetown University's Data Science Certificate Program, where she teaches Visual Analytics. Dr. Bilbro earned her doctorate from the University of Illinois, Urbana-Champaign, where her research centered on communication and visualization practices ...

XBUS-512 - Introduction to AI and Deep Learning at School of Continuing Studies

This course has no confirmed dates in the future. Subscribe to be notified when it is offered.


Something went wrong. We're trying to fix this error.

Thank you

Someone from the Coursalytics team will be in touch with you soon.

Disclaimer

Coursalytics is an independent platform to find, compare, and book executive courses. Coursalytics is not endorsed by, sponsored by, or otherwise affiliated with any business school or university.

Full disclaimer.

Because of COVID-19, many providers are cancelling or postponing in-person programs or providing online participation options.

We are happy to help you find a suitable online alternative.