{"id":5972,"date":"2025-04-13T20:51:43","date_gmt":"2025-04-14T00:51:43","guid":{"rendered":"https:\/\/engineering.jhu.edu\/ExecEd\/?post_type=course&p=5972"},"modified":"2025-07-01T14:33:14","modified_gmt":"2025-07-01T18:33:14","slug":"jhu-online-course-mastering-neural-networks-and-model-regularization","status":"publish","type":"course","link":"https:\/\/engineering.jhu.edu\/ExecEd\/course\/jhu-online-course-mastering-neural-networks-and-model-regularization\/","title":{"rendered":"Mastering Neural Networks and Model Regularization"},"content":{"rendered":"\n
\n\n
\n

Mastering Neural Networks and Model Regularization<\/h1>\n\n\n
<\/div>\n\n\n\n

Start anytime. Learn at your own pace.<\/p>\n\n\n

Use deep learning to uncover answers that used to be out of reach. <\/p>\n\n\n

\n
Start Now<\/a><\/div>\n<\/div>\n\n\n\n
Request Info<\/a>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n\n\n\n
\n
\"\"<\/figure>\n\n
\n\n
\n
\n

<\/rect><\/g><\/path><\/g><\/polygon><\/polygon><\/polygon><\/g><\/svg><\/span>Artificial Intelligence<\/span><\/span><\/p>\n\n\n\n

<\/title><\/path><\/path><\/path><\/circle><\/svg><\/span>Online Self-Paced<\/span><\/span><\/p>\n<\/div>\n\n\n\n
\n\n\n\n<\/div>\n<\/div>\n\n\n\n
<\/div>\n\n\n\n

Instructor: Dr. Erhan Guven<\/a><\/p>\n\n<\/div><\/div>\n<\/div>\n\n\n

\n\n
\n

<\/path><\/svg><\/span>Curriculum designed and delivered by Hopkins APL’s Dr. Erhan Guven<\/a><\/span><\/p>\n\n\n\n

<\/path><\/svg><\/span>LIVE monthly seminars and office hours<\/a> <\/span><\/p>\n\n\n\n

<\/path><\/svg><\/span>Engaging learning including video walkthroughs and hands-on activities<\/a><\/span><\/p>\n\n\n\n

<\/path><\/svg><\/span>Satisfaction guaranteed<\/a>. Explore the course with no risk.<\/strong><\/span><\/p>\n<\/div>\n\n<\/div><\/div>\n\n<\/div>\n\n

\n\n
\n\n
\n

Traditional machine learning\u2014built on structured data, optimized with ensembles, and tuned with regularization\u2014works well when the data is clean and the features are clearly defined\u2026 but in many real-world scenarios, that’s just not possible.

That’s where deep learning comes in.

For the final course in the Certificate in Theoretical Foundations of Machine Learning<\/a><\/a>, Dr. Erhan Guven guides you through today\u2019s most powerful AI systems that teach how machines to see, hear, and understand the world. Learn how to build the models that find their own way.

You\u2019ll start by building neural networks from scratch to understand how they learn, step by step, through backpropagation. Then, using PyTorch, you\u2019ll construct deeper architectures that learn directly from raw data: convolutional networks that can classify images and spectral models that can detect patterns in audio.

You\u2019ll also confront the real challenges that come with depth: overfitting, vanishing gradients, and high computational cost\u2014and learn how to address them with dropout, batch normalization, and GPU-based training.

These complex topics are broken down into hands-on projects, with Jupyter notebooks<\/a>, video lessons, readings and quizzes\u2014and Dr. Guven’s office hours are your chance get answers to any questions you have.

Deep learning changes the way models learn and what they can handle. Instead of relying on manual preprocessing or feature engineering, you\u2019ll train systems that extract structure on their own\u2014even from noisy, complex, or high-dimensional data. And by the end of the course, you\u2019ll be able to recognize when deep learning is the right tool\u2014and how to use it effectively.<\/p>\n<\/div>\n\n\n\n

\n

Prerequisites <\/strong><\/h2>\n\n\n\n

Experience with supervised machine learning, including model training, evaluation, and feature selection. Comfort with Python, vectorized operations, and basic linear algebra is recommended. No prior deep learning experience required\u2014but you should be confident coding and experimenting in a notebook environment.<\/p>\n<\/div>\n\n\n\n

\n

No Risk: Satisfaction Guaranteed<\/strong><\/h2>\n\n\n\n

Feel confident in your learning journey! If the course content is too advanced, not advanced enough<\/em>, or simply doesn\u2019t meet your expectations, we\u2019ve got you covered with our money-back guarantee. Just contact our team within 7 days from purchase to receive a full refund\u2014no questions asked.<\/strong> <\/p>\n<\/div>\n\n\n\n

\n
\n

Meet Your Instructor<\/strong><\/h2>\n\n\n\n

Dr. Erhan Guven<\/h3>\n\n\n\n

Johns Hopkins University, Johns Hopkins Applied Physics Laboratory<\/em><\/p>\n<\/div>\n\n\n\n

\n
\n\n<\/div>\n\n\n\n

Dr. Guven is an AI scientist at Johns Hopkins University Applied Physics Laboratory and assistant program manager in Johns Hopkins Engineering’s #1 ranked online master’s programs in AI and data science. His research spans a broad spectrum of machine learning applications, including large language models, financial systems cybersecurity, NLP, and bioinformatics. In his spare time, he enjoys gardening, beekeeping, building computers and playing Defense of the Ancients. <\/p>\n<\/div>\n\n\n\n

Dr. Guven is Here to Help!<\/strong><\/h4>\n\n\n\n

Questions about course content? Looking compare model results or get feedback? Stop by monthly Zoom office hours<\/strong> to talk with Erhan and fellow students.<\/p>\n<\/div>\n\n\n\n

\n

Projects You’ll Build (With Expert Guidance)<\/strong><\/h2>\n\n\n\n

With ready-to-use Jupyter notebooks and working code examples, Dr. Guven will walk you through creating…<\/p>\n\n\n\n