Scribd
Upload
104 views

Agenda: 1. What Is Tensorflow?

This document provides an agenda for an introduction to TensorFlow presentation. The agenda includes discussing what TensorFlow is, why you would use it, how it works with a demo, and CloudML. TensorFlow was originally developed by Google Brain to define functions on tensors and compute derivatives automatically using data flow graphs. It is an open source library for numerical computation that represents computations as graphs with nodes as operations and edges as tensors.

Uploaded by

SivaCharan
Copyright
© © All Rights Reserved
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
104 views

Agenda: 1. What Is Tensorflow?

This document provides an agenda for an introduction to TensorFlow presentation. The agenda includes discussing what TensorFlow is, why you would use it, how it works with a demo, and CloudML. TensorFlow was originally developed by Google Brain to define functions on tensors and compute derivatives automatically using data flow graphs. It is an open source library for numerical computation that represents computations as graphs with nodes as operations and edges as tensors.

Uploaded by

SivaCharan
Copyright
© © All Rights Reserved
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 10

Agenda

1. What is TensorFlow?

2. Why would you use it?

3. How does itwork? + Demo

4. CloudML (alpha) discussion

Introduction to TensorFlow 1
TensorFlow
Google TensorFlow

● Originally developed by the Google


Brain Team within Google's Machine
Intelligence research organization

● TensorFlow provides primitives for


defining functions on tensors and PLACE IMAGEHERE
automatically computing their
derivatives.

● An open source software library for


numerical computation using data
flow graphs

4
Tensor
Simply put: Tensors can be viewed as a
multidimensional array of numbers.
This means that:

● A scalar is a tensor,

● A vector is a tensor,

● A matrix is a tensor

● ...

3
Data Flow Graph?
● Computations are represented as graphs:
● Nodes are the operations(ops)
● Edges are the Tensors
(multidimensional arrays)

● Typical program consists of 2 phases:


● construction phase: assembling a
graph (model)
● execution phase:
pushing data through thegraph

4
Agenda
1. What is TensorFlow?

2. Why would you use it?

3. How does itwork? + Demo

4. CloudML (alpha) discussion

Introduction to TensorFlow 17
Why would you use NN / Deep Learning?
● Neural Networks (NNs) are universal
function approximators that work very
well with huge datasets
● NNs / deep networks do unsupervised
feature learning

● Track record, being SotA in:


○ image classification,
○ language processing,
○ speech recognition,
○ ...

Introduction to TensorFlow 18
Why TensorFlow?
There are a lot of alternatives:

● Torch
● Caffe
● Theano (Keras, Lasagne)
● CuDNN
● Mxnet
● DSSTNE
● DL4J
● DIANNE
● Etc.

19
TensorFlow has the largestcommunity

Sources: http://deliprao.com/archives/168
http://www.slideshare.net/JenAman/large-scale-deep-learning-wit
Introduction to TensorFlow h-tensorflow 20
TensorFlow is very portable/scalable
Runs on CPUs, GPUs, TPUs over one or more
machines, but also on phones(android+iOS)
and raspberry pi’s...

Introduction to TensorFlow 9
TensorFlow is more than an R&D project
- Specific functionalities for deployment (TF Serving /
CloudML)
- Easier/more documentation (for more general public)
- Included visualization tool (Tensorboard)
- Simplified interfaces like SKFlow

Introduction to TensorFlow 10

You might also like