Congratulations!

Introduction to TensorFlow in Python

Isaiah Hull

Visiting Associate Professor of Finance, BI Norwegian Business School

What you learned

Chapter 1
- Low-level, basic, and advanced operations
- Graph-based computation
- Gradient computation and optimization
Chapter 2
- Data loading and transformation
- Predefined and custom loss functions
- Linear models and batch training

Chapter 3
- Dense neural network layers
- Activation functions
- Optimization algorithms
- Training neural networks
Chapter 4
- Neural networks in Keras
- Training and validation
- The Estimators API

This image shows a screenshot of models returned from a TensorFlow Hub search.

TensorFlow Probability
- More statistical distributions
- Trainable distributions
- Extended set of optimizers

This image shows a histogram with a fitted probability distribution.

¹ Screenshot from https://tfhub.dev.

TensorFlow 2.0
- eager_execution()
- Tighter keras integration
- Estimators
- function()

This image shows a schematic of the Estimators API and how it relates to lower level APIs.

This image shows a diagram of a neural network.

The image shows a static graph in TensorFlow.

¹ Screenshot taken from https://www.tensorflow.org/guide/premade_estimators

Introduction to TensorFlow in Python