About Generative Adversarial Networks and Variational Autoencoders:
Deep Learning is one of the most exciting and promising segments of Artificial Intelligence and machine learning technologies. This deep learning course with Generative Adversarial Networks is designed to help you master deep learning techniques and build deep learning models using TensorFlow.
Variational autoencoders and GANs have been 2 of the most interesting developments in deep learning and machine learning recently. GAN stands for generative adversarial network, where 2 neural networks compete with each other.
What is unsupervised learning?
Unsupervised learning means we’re not trying to map input data to targets, we’re just trying to learn the structure of that input data. Once we’ve learned that structure, we can do some pretty cool things. One example is generating audio data from an existing audio data.
In this first course,er wanted to learn the structure of data in order to improve supervised training, which we demonstrated was possible. In this new course, we want to learn the structure of data in order to produce more stuff that resembles the original data.
Advancements in deep learning are being seen in smart phone applications, creating efficiencies in the power grid, driving advancements in healthcare, improving agricultural yields, and helping us find solutions to climate change.
What you'll learn ?
- The basic principles of generative models
- Build a variational autoencoder in Theano and Tensorflow
- Build a GAN (Generative Adversarial Network) in Theano and Tensorflow
- Learn to understand and implement the DCGAN model to simulate realistic images, the inventor of GANS (generative adversarial networks).
- Know how to build a neural network in Theano and/or Tensorflow
- Multivariate Calculus
- Numpy, etc.
- Identify the deep learning algorithm : Generative adversarial Networks which is more appropriate for various types of learning tasks in various domains.
- Implement GANs and solve real-world problems.