Deep learning is driving advances in artificial intelligence that are changing our world. Enroll now to build and apply your own deep neural networks to challenges like image classification and generation, time-series prediction, and model deployment.

Necessary preparation

• This program has been created specifically for students who are interested in machine learning, AI, and/or deep learning, and who have a basic working knowledge of Python programming. Outside of that Python expectation, it’s a very beginner-friendly program.

For those who want to

• Become an expert in neural networks.
• Learn to implement them using the deep learning framework PyTorch.
• Build convolutional networks for image recognition, recurrent networks for sequence generation, generative adversarial networks for image generation.
• Learn how to deploy models accessible from a website.

The Program 

1. Introduction.
2. Neural Networks
3. Convolutional Neural Networks.
4. Recurrent Neural Networks
5. Generative Adversarial Networks
6. Deploying a Sentiment Analysis Model

What will you learn

• To use development tools such as Anaconda and Jupyter notebooks.
• Neural networks basics, and build your first network with Python and NumPy.
•  Use the modern deep learning framework PyTorch to build multi-layer neural networks, and analyze real data.
• How to build convolutional networks and use them to classify images (faces, melanomas, etc.) based on patterns and objects that appear in them. 
• Data compression and image denoising.
• Build your own recurrent networks and long short-term memory networks with PyTorch; perform sentiment analysis and use recurrent networks to generate new text from TV scripts.
• Understand and implement a Deep Convolutional GAN (generative adversarial network) to generate realistic images, with Ian Goodfellow, the inventor of GANs, and Jun-Yan Zhu, the creator of CycleGANs.
• Build a model, deploy it, and create a gateway for accessing it from a website.