Deep Learning

Deep learning is a method in artificial intelligence (AI) that teaches computers to process data in a way that is inspired by the human brain. Deep learning models can recognise complex patterns in pictures, text, sounds, and other data to produce accurate insights and predictions (AWS). Throughout this course, you will be provided with a strong introduction to the world of artificial intelligence. Delve into cutting-edge subjects like neural networks, convolutional neural networks, recurrent neural networks and generative adversarial networks.  

Throughout the program, you will also have the opportunity to work on projects using PyTorch, further enhancing your practical knowledge. Be part of the upcoming wave of deep learning experts who will shape an AI-driven future.

This Deep Learning course will be delivered to you in partnership with Udacity, meaning you'll have access to both Udacity's learning and career services as well as RMIT Online's course enablement support through our Learner Success team.

This Deep Learning course is ideal for: 

• Existing data specialists, wanting to gain exposure to the potential of AI and ML solutions, leverage neural networks, and build complex learning models.
• Aspiring AI developers with foundational skills in Python looking to build upon their technical skills towards developing and defining cutting-edge solutions powered by AI.  

By the end of this course, you'll be able to: 

• Create a simple neural network (NN) using PyTorch to predict patterns from real data.
• Build convolutional neural networks (CNNs) to classify landmark images based on patterns and objects that appear in them.
• Implement a recurrent neural network (RNN) and its variants (LSTMs, GRUs) with PyTorch to build a customer service chatbot.

During this course, you will use your newly acquired Deep Learning skills to complete 4 projects. 

Your first project will look at developing a handwritten digit Classifyer with PyTourch. Your second project focuses on landmark classification and tagging for social media. Your third project is a LSTM Seq2Seq Chatbot and your final project is a Face Generation project where you will build and train a custom GAN architecture on the CelebA dataset. 

After completing this course, you’ll walk away with an RMIT credential which can be validated, recognised, and shared on social media platforms.

For Deep Learning, students should have experience working with and/or knowledge of the following topics: 

• Derivatives 
• Linear Algebra 
• Numpy, Pandas 
• Intermediate Python 
• Jupyter notebooks