TensorFlow Introduction

We can think of ________ as variables, where we only define the type and dimension, but do not assign the value.

placeholders

TensorFlow's visualization toolkit

It provides the visualization and tooling needed for machine learning experimentation:

What is the main reasons of increasing popularity of Deep Learning? The advances in machine learning algorithms and research. The availability of massive amounts of data for training computer systems. The dramatic increases in computer processing capabilities. All of the above

All of the above are increasing the popularity of DL

Three parts of the TensorFlow architecture

The data is preprocessed, The model is built, The model is trained and estimated.

Why is TensorFlow the proper library for Deep Learning? It will benefit from TensorFlow's auto-differentiation and suite of first-rate optimizers It provides a collection of trainable mathematical functions that are useful for neural networks. It has extensive built-in support for deep learning All of the above

All of the above make TensorFlow the proper library for DL

What are the benefits of Keras's Functional API (select 3 answers)?

It can handle models with non-linear topology, It can handle models with shared layers, It can handle models with multiple inputs or outputs

Tensor structure

It helps us by giving us the freedom to shape the dataset in the way we want. It is particularly helpful when dealing with images, due to the nature of how information in images are encoded.

What is a Data Flow Graph?

A representation of data dependencies between operations

TensorFlow

It is a free and open-source software library for machine learning and artificial intelligence. It can be used across a range of tasks but has a particular focus on training and inference of deep neural

Which statement is TRUE about TensorFlow?

Runs on CPU and GPU

Which statement is FALSE about TensorFlow?

TensorFlow library is not proper for handling Machine Learning Problems

Keras is a high level API for building deep learning models. It provides limited control over the different nodes and layers in a network.

True - It is a high level API

In TensorFlow, tensors are multi-dimensional arrays with a uniform type (called a dtype). All tensors are immutable like Python numbers and strings: you can never update the contents of a tensor, only create a new one.

True - They are immutable and you can only create a new one

Fundamental elements of TensorFlow

Variables, Constants, Placeholders

Name two properties that a tensor has

a datatype and a shape

__________ cannot have their values changed.

constants

Session

it is used for executing the graph operations

________ are containers used to store values.

variables