Practicum for Deep Neural Networks
In the last decade, Neural Networks (NN) have attracted a lot of research due to their immense application potential. Breakthroughs of Deep Learning in image classification, speech recognition, and other challenging areas have provided the best solutions to many problems and significantly advanced “state of the art” AI machines in their ability to learn from data.
This course will introduce students to fundamental concepts of Deep Neural Network (DNN) development. It will cover important algorithms and modelling used in the development of these networks. Utilizing rich sets of available NN models, we will perform detailed analysis of leading ML approaches and popular NN like CNN, FCNN, ImageNet, ResNet, and RNN. TensorFlow framework exercises will develop practical skills, allowing students to gain confidence in understanding what ML concepts mean in the neural network spaces. By the end of this course you will have learned important concepts and developed skill necessary to create and train neural networks for specific practical problems.
- Train a simple deep NN
- Learn regularization and optimization of NN
- Apply NN in image classification, image segmentation and natural language processing (NLP)
- Write applications in TensorFlow for practical neural networks
- Opens career opportunities in one of most desirable fields today for ML/AI curriculum
Course typically offered: Online during our Summer and Winter academic quarters.
Prerequisites: CSE-41287: Linear Algebra for Machine Learning and CSE-41305: Probability and Statistics for Deep Learning, or equivilent knowledge.
Next Steps: Upon completion, consider additional coursework in our specialized certificate in Machine Learning Methods to continue learning.
More Information: For more information about this course, please contact email@example.com.
Course Number: CSE-41311
Credit: 3.00 unit(s)
Related Certificate Programs: Machine Learning Methods
+ Expand All
1/11/2021 - 3/12/2021