Learn how to build deep learning applications with TensorFlow. This course was developed by the TensorFlow team and Udacity as a practical approach to deep learning for software developers. You'll get hands-on experience building your own state-of-the-art image classifiers and other deep learning models. You'll also use your TensorFlow models in the real world on mobile devices, in the cloud, and in browsers. Finally, you'll use advanced techniques and algorithms to work with large datasets. By the end of this course, you'll have all the skills necessary to start creating your own AI applications.
Overview
Syllabus
- Introduction to Machine Learning
- Get a high-level overview of artificial intelligence and machine learning,Learn how machine learning and deep learning have revolutionized software
- Your First Model: Fashion MNIST
- Build a neural network that can recognize images of articles of clothing
- Introduction to Convolutional Neural Networks ("CNNs")
- Use a convolutional network to build more efficient models for Fashion MNIST
- Going Further with CNNs
- Expand your image classifiers into models that can predict from multiple classes,Use a convolutional network to build a classifier for more detailed color images
- Transfer Learning
- Use a pre-trained network to build powerful state-of-the-art classifiers
- Saving and Loading Models
- Look at the new SAVEDMODEL format in TensorFlow 2.0 and take advantage of it for TensorFlow-Lite and TensorFlow-Serving
- Time Series Forecasting
- Learning from sequential data with recurrent neural networks
- Natural Language Processing
- Tokenize words and create embeddings for using text data with neural networks,Build recurrent neural networks, such as LSTMs, for improved NLP models,Generate new text for tasks like novel song lyrics
- Introduction to TensorFlow Lite
- Learn how you can use TensorFlow lite to build machine learning apps on Android, iOS and iOT devices
Taught by
Magnus Hyttsten, Juan Delgado and Paige Bailey
