Current Status

Not Enrolled

Price

Closed

Get Started

Deep learning has become one of the most important techniques used to address computer vision tasks for autonomous vehicles. Nowadays, using deep learning methodologies, autonomous vehicles are able to gather and process large amounts of data, perform advanced perception, and make complex decisions. This module will provide you a clear understanding of the foundational concepts in deep learning, challenges, applications, and the role that deep learning is playing in the rapid advancement of the field. This module will present, in terms of theory and practice, the fundamental concepts of deep learning, including the foundations of neural network architectures, learning techniques, and architectures.

What You’ll Learn

  • Gain a fundamental understanding of deep learning
  • Understand the basic theory of neural networks
  • Learn different learning techniques
  • Identify key architecture parameters
  • Build and train deep neural networks

Module Content

Module kick-off
Reading list for background in mathematics and deep learning
Introduction to deep learning
Overview, history and challenges for deep learning [11:09]
Basic theory
Neural networks [13:59]
Activation functions [06:33]
Loss functions [08:29]
Backpropagation [11:02]
Learning techniques
Regularization and normalization [15:56]
Supervised learning [09:18]
Datasets [09:06]
Transfer learning [12:11]
Types of neural networks
Self-supervised and unsupervised learning [10:33]
Introduction to Convolutional Neural Networks (CNNs) [44:09]
Applications of CNNs [16:53]
Introduction to Recurrent Neural Networks (RNNs) [29:28]
HOMEWORK
Applications of RNNs [07:08]
Prep work reading list, to help prepare for below exercises
Optional Advanced Reading
Access the 2-part homework tasks
End of module reading list, based on more advanced content (optional)
Group session recordings
Deep Learning and AI end of module test
Passes0
There are no passes in your basket!
0