Learn how to use a Colab notebook to create a custom ML classification model built on TensorFlow using the Keras machine learning library.
- [Instructor] If you're like me you might be feeling…a little bit intimidated by the code underlying TensorFlow…and you wouldn't be alone in this.…Because there has been so much demand for a higher level…library to make these deep neural network technologies…more accessible to people who maybe haven't had…as an extensive of a machine learning background.…There's a very popular library called Keras…that's often used for TensorFlow…and actually other deep neural network…custom machine learning algorithms.…
So Keras is an open source neural network library,…it's in Python and it's designed to be user friendly,…human readable, modular and extensible.…It's runs on top of not only TensorFlow…but also other deep neural networks…such as Microsoft Cognitive Toolkit or Theano,…and the idea is it enables faster experimentation…with deep neural networks.…As you might have intiuted looking at the amount…of parameters that we saw in the previous sections,…there is a lot of back and forth in terms…of deep neural networks, in terms of the input data,…
- Hosting options: Serverless, containers, and virtual machines
- Enabling the GCP ML AIs
- Preparing data with Cloud Dataflow and Dataprep
- Modeling predictions for images, video, text to speech, and cloud translation
- Machine learning with AutoML
- Advanced machine learning and deep learning
- Machine learning architectures
Skill Level Intermediate
1. Machine Learning on Google Cloud Platform
2. Machine Learning API Services
3. Machine Learning with AutoML
Understand AutoML Vision4m 57s
4. Advanced Machine Learning
5. Machine Learning Architectures
Next steps1m 30s
- Mark as unwatched
- Mark all as unwatched
Are you sure you want to mark all the videos in this course as unwatched?
This will not affect your course history, your reports, or your certificates of completion for this course.Cancel
Take notes with your new membership!
Type in the entry box, then click Enter to save your note.
1:30Press on any video thumbnail to jump immediately to the timecode shown.
Notes are saved with you account but can also be exported as plain text, MS Word, PDF, Google Doc, or Evernote.