Applied Deep Learning with Python
This course demonstrates an applied approach to deep learning, through image identification and image generation based applications.
This title is part of the Deep Learning Mini-Degree
This course takes an applied approach to deep learning, featuring a step-by-step guide that shows you how to build two web apps – one which identifies uploaded images by comparing it to a library of images, and another which generates images based upon a training set. Using Python, Flask, and Keras backed by Tensorflow, you will learn skills that will enable you to better identify, understand, and debug issues that can arise during the training process, ensuring that your deep learning models will perform better ever before.
What you will learn
- Dataset Augmentation – making the most out of a limited dataset
- Parameter Updating – ensure your models remain state of the art
- Tips and tricks to deal with common problems, such as overfitting, or dealing with convolutional networks of varying sizes
- An introduction to Flask – a framework that allows you to create these web apps
About the Deep Learning Mini-Degree
The Deep Learning Mini-Degree is an on-demand learning curriculum composed of 6 professional-grade courses geared towards teaching you how to solve real-world problems and build innovative projects using Machine Learning and Python. Learn and understand the fundamentals necessary to build the next generation of intelligent applications and software, with concepts and theory that can be applied across technology and frameworks.
Challenge yourself by joining this exciting project-based curriculum and gain the knowledge and abilities required to succeed in this brand new industry. No prior experience with AI or Machine Learning is necessary to join. However, basic to intermediate Python skills are assumed in all of the courses.
What Our Members Are Saying
- Intermediate Python programming skills
- Familiarity with Artificial Neural Networks
- Familiarity with Convolutional Neural Networks
- Familiarity with Generative Adversarial Networks