Introduction to TensorFlow 2.0
Learn the basics of machine learning and deep learning using TensorFlow 2.0
TensorFlow is a popular open source machine learning software developed by Google’s Brain team. It boasts a collection of visualization tools and can run on multiple GPUs, CPUs, and mobile operating systems.
Expert Dylan Bargteil leads a deep dive into the core concepts in machine learning and TensorFlow, with a focus on neural networks. You’ll learn how to build and launch graphs in TensorFlow, evaluate model performance, and manage overfitting. And you’ll gain a deep understanding of how neural networks work, including more complex architectures such as convolutional neural networks and recurrent neural networks. Join in to develop your ability to build models suitable for classification and regression tasks using structured and unstructured data such as tables, text, images, and timeseries data, as well as data of mixed structure and type.
What you'll learnand how you can apply it
By the end of this live online course, you’ll understand:
 Machine learning, neural network, deep learning, and artificial intelligence basic concepts
 What TensorFlow is and what applications it’s good for
 How to build predictive models using a mix of structured and unstructured datasets
 Where neural network architecture has been extended for more complex modeling
And you’ll be able to:
 Create statistical models for classification and regression using TensorFlow
 Evaluate the benefits and disadvantages of using TensorFlow over other machine learning software
 Document, save, share, and recreate models using TensorFlow’s Keras API
 Design model architectures that combine data sources and types for predictions in complex contexts
This training course is for you because...
 You’re a software engineer or programmer with a background in Python, and you want to develop a basic understanding of machine learning.
 You have experience in modeling or data science, and you want to learn TensorFlow.
 You’re in a nontechnical role, and you want to effectively communicate with engineers and data scientists about TensorFlow and neural networks.
Prerequisites
 Experience with Python, including NumPy
 Familiarity with matrices, linear algebra, and machine learning
Recommended preparation:
 Read “Exploratory Data Analysis” and “Data and Sampling Distributions” (chapters 1 and 2 in Practical Statistics for Data Scientists)
Recommended followup:
 Read “Training Large Deep Networks” (chapter 9 in TensorFlow for Deep Learning)
About your instructor

Dylan Bargteil is a data scientist in residence at The Data Incubator, where he continues his researchguided curriculum development and instruction. Previously, he worked with deep learning models to assist surgical robots. He studied physics and math at the University of Maryland, where he was a research and teaching assistant developing a new introductory physics curriculum and pedagogy in partnership with HHMI, and earned his PhD in physics from New York University.
Schedule
The timeframes are only estimates and may vary according to how the class is progressing
Introduction to TensorFlow (60 minutes)
 Lecture: Machine learning and gradient descent; tensors and automatic differentiation; the TensorFlow API
 Handson exercises: Use tensors to compute statistical aggregates; use automatic differentiation to minimize functions; extend the example of univariate linear regression in TensorFlow to a multivariate linear regression
 Q&A
Break (5 minutes)
Computation graphs (40 minutes)
 Lecture: Optimizing computations with TensorFlow AutoGraph; accelerators (GPUs/TPUs)
 Handson exercise: Use AutoGraph to accelerate the fit method
 Q&A
Break (5 minutes)
Neural networks (55 minutes)
 Lecture: Logistic regression and neurons; neural networks
 Handson exercise: Extend a logistic regressor to perform multiclass classification; experiment with the size of a hidden layer in a neural network designed for the XOR classification task Q&A
Break (5 minutes)
Deep learning (60 minutes)
 Lecture: Keras API; stochastic gradient descent; overfitting
 Handson exercise: Perform hyperparameter tuning of a neural network
Wrapup and Q&A (10 minutes)