PyTorch and Deep Learning for Decision Makers

This course introduces you to PyTorch, one of the most popular deep learning frameworks, revealing how it can be used in your company to automate and optimize processes through the development and deployment of state-of-the-art AI applications. The course will help you identify the most common use cases of AI in the industry and how PyTorch’s ecosystem and the commoditization of deep learning models can help you integrate them into your business. You will also learn why ensuring data quality is critical for the successful deployment of AI applications, and why getting the right data should be the top priority for any AI project. The course will discuss several trade-offs involved in choosing the appropriate model for the task at hand: build vs. buy, black vs. white box, and the risk and cost of delivering wrong predictions.

Finally, the course will discuss what happens after an AI application is deployed, addressing topics such as the inherent limitations of AI models, the mitigation of risks and vulnerabilities, and the challenge of data privacy.

This course targets technical and non-technical individuals interested in understanding how deep learning and PyTorch can be used to create business value through the development and deployment of AI applications.

LFS116x provides an overview of the AI landscape, focusing on PyTorch’s ecosystem, while giving you a solid understanding of AI’s current capabilities and it will help you make informed decisions about the development and maintenance of AI projects while taking in consideration key aspects related to data quality, model performance, and security.

• Discuss typical use cases of AI across industries

• Understand the role and importance of PyTorch in the current AI landscape

• Discuss the importance of data quality and its overall impact on the performance of a model or application

• Understand the trade-offs involved in developing or buying a model or application

• Identify the challenges and risks involved in deploying an application: biases, attacks, privacy issues, and more