SlideShare una empresa de Scribd logo
1 de 26
Descargar para leer sin conexión
The TensorFlow dance
craze
Gabe Hamilton
TensorFlow is a
Machine Learning library
What is Machine Learning?
usually: Statistical Pattern Matching
Using past measurements to predict something
about a new piece of information
Does this picture contain a cat? Classification
How much is this home worth? Regression
Regression Talk
https://docs.google.com/presentation/d/17FoojZ17DKDZqoByhB16PmtAXtnJ
tXSy1-feK9-A_fg/edit#slide=id.p10
There are lots of other ML libraries
Is it right for you?
Maybe Not, use Prediction API
http://www.slideshare.net/gabehamilton/intro-to-google-prediction-api-15167420
Or equivalent Amazon or Microsoft APIs
if you have a CSV of observed data.
But I’d like to get into the
details or I am working on
a complex problem...
You do still have some
choices.
Some people prefer Keras on top of TensorFlow
https://keras.io/ or tf-slim or pretty-tensor
So why use TensorFlow?
It’s not much different than the “easier” libraries.
You’ll want to understand more and more details anyway.
Because you like
It has the hottest dance moves!
Look out a Tensor!
Some Math and a Multi-Dimensional Array had a baby
For our purposes
It’s a multi-dimensional array.
Just remember that you are
putting a mathematical construct
in that array.
A tensor is a multi-dimensional
array with certain transformation
properties
You have some data
Even though it’s in a 2D spreadsheet it can
describe a multidimensional space.
House Price Data
1 mile to park
2 bedrooms
1800 sq ft
So our Tensor is [1, 2, 1800]Square footage
Distance to park
# of bathrooms
Let’s build a Tensor Machine
= a Tensor
Comparing output
is our Output
But we are expecting
- = Loss
Iterate until we have a good model
Demo
Simple Regression
https://github.com/gabehamilton/code-from-talks/tree/master/tensorflow_intro
Demo
(run in Datalab)
Demo code: fitting a line to points
Demo is of Datalab notebook
# Create 100 phony x, y data points in NumPy, y = x * 0.1 + 0.3
tf.reset_default_graph()
import numpy as np
import matplotlib.pyplot as plt
%matplotlib inline
x_measured = np.random.rand(100).astype(np.float32)
y_measured = x_measured * (0.1 + (0.05 *np.random.rand(100))) + 0.3
plt.scatter(x_measured, y_measured)
plt.xlabel('<- Bluer : Uniform Color : Redder ->')
plt.ylabel('Deaths per mission')
plt.title('Star Trek Uniform Color Mortality Incidence')
# plt.plot([0, 1], [0, 0.5], color='purple', lw=2)
# plt.plot([0, 1], [0.25, 0.5], color='purple', lw=2)
Measured Data
Demo code continued
import tensorflow as tf
# Try to find values for slope and offset that match
# y_measured = slope * x_measured + offset
slope = tf.Variable(tf.random_uniform([1], -1.0, 1.0))
offset = tf.Variable(tf.zeros([1]))
y_predicted = slope * x_measured + offset
loss = tf.reduce_mean(tf.square(y_predicted - y_measured))
optimizer = tf.train.GradientDescentOptimizer(0.5)
train = optimizer.minimize(loss)
A test value for slope
Demo code continued
# Launch the graph.
sess = tf.Session()
sess.run(tf.initialize_all_variables()) # and initialize variables
# Fit the line.
print 'step #t', 'slopett', 'offset'
for step in range(201):
sess.run(train)
if step % 20 == 0:
print step,'t', sess.run(slope)[0], 't', sess.run(offset)[0]
A test value for slope and offset
Q & A
Plus more slides for longer talks or
answering questions
Why TensorFlow is useful
Build your graph in a high level language,
execute in fast implementations.
Distribute graph operations across processors.
Whole graph can be optimized.
4+ D Spaces
A given measurement all fits into a simple Tensor: [4, 4, 4, 3]
Some Tensors
Scalar 0.2
Vector [1, 2, 1800]
Matrix
[2, 1, 1],
[1, 2, 0],
[0, 1, 0]
n-Tensors
Rank 2 Tensor
When a bunch of
vectors hang out
they make a Matrix
[2, 1, 1],
[1, 2, 0],
[0, 1, 0]

Más contenido relacionado

La actualidad más candente

Your first TensorFlow programming with Jupyter
Your first TensorFlow programming with JupyterYour first TensorFlow programming with Jupyter
Your first TensorFlow programming with JupyterEtsuji Nakai
 
Matplotlib 簡介與使用
Matplotlib 簡介與使用Matplotlib 簡介與使用
Matplotlib 簡介與使用Vic Yang
 
The matplotlib Library
The matplotlib LibraryThe matplotlib Library
The matplotlib LibraryHaim Michael
 
Tensorflow windows installation
Tensorflow windows installationTensorflow windows installation
Tensorflow windows installationmarwa Ayad Mohamed
 
Effective Numerical Computation in NumPy and SciPy
Effective Numerical Computation in NumPy and SciPyEffective Numerical Computation in NumPy and SciPy
Effective Numerical Computation in NumPy and SciPyKimikazu Kato
 
Rajat Monga at AI Frontiers: Deep Learning with TensorFlow
Rajat Monga at AI Frontiers: Deep Learning with TensorFlowRajat Monga at AI Frontiers: Deep Learning with TensorFlow
Rajat Monga at AI Frontiers: Deep Learning with TensorFlowAI Frontiers
 
機械学習によるデータ分析 実践編
機械学習によるデータ分析 実践編機械学習によるデータ分析 実践編
機械学習によるデータ分析 実践編Ryota Kamoshida
 
Introduction to Pylab and Matploitlib.
Introduction to Pylab and Matploitlib. Introduction to Pylab and Matploitlib.
Introduction to Pylab and Matploitlib. yazad dumasia
 
Malloc() and calloc() in c
Malloc() and calloc() in cMalloc() and calloc() in c
Malloc() and calloc() in cMahesh Tibrewal
 
computer notes - Data Structures - 8
computer notes - Data Structures - 8computer notes - Data Structures - 8
computer notes - Data Structures - 8ecomputernotes
 
Introduction to Iteratees (Scala)
Introduction to Iteratees (Scala)Introduction to Iteratees (Scala)
Introduction to Iteratees (Scala)Alexander Lehmann
 
Memory management CP
Memory management  CPMemory management  CP
Memory management CPShubham Sinha
 

La actualidad más candente (20)

Your first TensorFlow programming with Jupyter
Your first TensorFlow programming with JupyterYour first TensorFlow programming with Jupyter
Your first TensorFlow programming with Jupyter
 
Matplotlib 簡介與使用
Matplotlib 簡介與使用Matplotlib 簡介與使用
Matplotlib 簡介與使用
 
The matplotlib Library
The matplotlib LibraryThe matplotlib Library
The matplotlib Library
 
Tensorflow windows installation
Tensorflow windows installationTensorflow windows installation
Tensorflow windows installation
 
NUMPY
NUMPY NUMPY
NUMPY
 
NumPy/SciPy Statistics
NumPy/SciPy StatisticsNumPy/SciPy Statistics
NumPy/SciPy Statistics
 
Py lecture5 python plots
Py lecture5 python plotsPy lecture5 python plots
Py lecture5 python plots
 
Effective Numerical Computation in NumPy and SciPy
Effective Numerical Computation in NumPy and SciPyEffective Numerical Computation in NumPy and SciPy
Effective Numerical Computation in NumPy and SciPy
 
Gnuplot 2
Gnuplot 2Gnuplot 2
Gnuplot 2
 
U3.stack queue
U3.stack queueU3.stack queue
U3.stack queue
 
Project gnuplot
Project gnuplotProject gnuplot
Project gnuplot
 
Rajat Monga at AI Frontiers: Deep Learning with TensorFlow
Rajat Monga at AI Frontiers: Deep Learning with TensorFlowRajat Monga at AI Frontiers: Deep Learning with TensorFlow
Rajat Monga at AI Frontiers: Deep Learning with TensorFlow
 
機械学習によるデータ分析 実践編
機械学習によるデータ分析 実践編機械学習によるデータ分析 実践編
機械学習によるデータ分析 実践編
 
Python Scipy Numpy
Python Scipy NumpyPython Scipy Numpy
Python Scipy Numpy
 
Introduction to Pylab and Matploitlib.
Introduction to Pylab and Matploitlib. Introduction to Pylab and Matploitlib.
Introduction to Pylab and Matploitlib.
 
Data Structures - Lecture 6 [queues]
Data Structures - Lecture 6 [queues]Data Structures - Lecture 6 [queues]
Data Structures - Lecture 6 [queues]
 
Malloc() and calloc() in c
Malloc() and calloc() in cMalloc() and calloc() in c
Malloc() and calloc() in c
 
computer notes - Data Structures - 8
computer notes - Data Structures - 8computer notes - Data Structures - 8
computer notes - Data Structures - 8
 
Introduction to Iteratees (Scala)
Introduction to Iteratees (Scala)Introduction to Iteratees (Scala)
Introduction to Iteratees (Scala)
 
Memory management CP
Memory management  CPMemory management  CP
Memory management CP
 

Similar a The TensorFlow dance craze

Introduction to Tensorflow
Introduction to TensorflowIntroduction to Tensorflow
Introduction to TensorflowTzar Umang
 
Deep Learning in your Browser: powered by WebGL
Deep Learning in your Browser: powered by WebGLDeep Learning in your Browser: powered by WebGL
Deep Learning in your Browser: powered by WebGLOswald Campesato
 
Introduction to Machine Learning
Introduction to Machine LearningIntroduction to Machine Learning
Introduction to Machine LearningBig_Data_Ukraine
 
TensorFlow for IITians
TensorFlow for IITiansTensorFlow for IITians
TensorFlow for IITiansAshish Bansal
 
Parallel Computing with R
Parallel Computing with RParallel Computing with R
Parallel Computing with RAbhirup Mallik
 
Regression Tree.pdf
Regression Tree.pdfRegression Tree.pdf
Regression Tree.pdfIvanHartana4
 
What is TensorFlow and why do we use it
What is TensorFlow and why do we use itWhat is TensorFlow and why do we use it
What is TensorFlow and why do we use itRobert John
 
error 2.pdf101316, 6(46 PM01_errorPage 1 of 5http.docx
error 2.pdf101316, 6(46 PM01_errorPage 1 of 5http.docxerror 2.pdf101316, 6(46 PM01_errorPage 1 of 5http.docx
error 2.pdf101316, 6(46 PM01_errorPage 1 of 5http.docxSALU18
 
Python seaborn cheat_sheet
Python seaborn cheat_sheetPython seaborn cheat_sheet
Python seaborn cheat_sheetNishant Upadhyay
 
TypeScript and Deep Learning
TypeScript and Deep LearningTypeScript and Deep Learning
TypeScript and Deep LearningOswald Campesato
 
Machine Learning and Go. Go!
Machine Learning and Go. Go!Machine Learning and Go. Go!
Machine Learning and Go. Go!Diana Ortega
 
Natural language processing open seminar For Tensorflow usage
Natural language processing open seminar For Tensorflow usageNatural language processing open seminar For Tensorflow usage
Natural language processing open seminar For Tensorflow usagehyunyoung Lee
 
Language translation with Deep Learning (RNN) with TensorFlow
Language translation with Deep Learning (RNN) with TensorFlowLanguage translation with Deep Learning (RNN) with TensorFlow
Language translation with Deep Learning (RNN) with TensorFlowS N
 
Advanced Spark and TensorFlow Meetup May 26, 2016
Advanced Spark and TensorFlow Meetup May 26, 2016Advanced Spark and TensorFlow Meetup May 26, 2016
Advanced Spark and TensorFlow Meetup May 26, 2016Chris Fregly
 
Tensorflow - Intro (2017)
Tensorflow - Intro (2017)Tensorflow - Intro (2017)
Tensorflow - Intro (2017)Alessio Tonioni
 
TensorFlow example for AI Ukraine2016
TensorFlow example  for AI Ukraine2016TensorFlow example  for AI Ukraine2016
TensorFlow example for AI Ukraine2016Andrii Babii
 
maXbox starter69 Machine Learning VII
maXbox starter69 Machine Learning VIImaXbox starter69 Machine Learning VII
maXbox starter69 Machine Learning VIIMax Kleiner
 
Deep Learning, Scala, and Spark
Deep Learning, Scala, and SparkDeep Learning, Scala, and Spark
Deep Learning, Scala, and SparkOswald Campesato
 
Introduction to Tensor Flow for Optical Character Recognition (OCR)
Introduction to Tensor Flow for Optical Character Recognition (OCR)Introduction to Tensor Flow for Optical Character Recognition (OCR)
Introduction to Tensor Flow for Optical Character Recognition (OCR)Vincenzo Santopietro
 

Similar a The TensorFlow dance craze (20)

Introduction to Tensorflow
Introduction to TensorflowIntroduction to Tensorflow
Introduction to Tensorflow
 
Deep Learning in your Browser: powered by WebGL
Deep Learning in your Browser: powered by WebGLDeep Learning in your Browser: powered by WebGL
Deep Learning in your Browser: powered by WebGL
 
Introduction to Machine Learning
Introduction to Machine LearningIntroduction to Machine Learning
Introduction to Machine Learning
 
TensorFlow for IITians
TensorFlow for IITiansTensorFlow for IITians
TensorFlow for IITians
 
Parallel Computing with R
Parallel Computing with RParallel Computing with R
Parallel Computing with R
 
Regression Tree.pdf
Regression Tree.pdfRegression Tree.pdf
Regression Tree.pdf
 
What is TensorFlow and why do we use it
What is TensorFlow and why do we use itWhat is TensorFlow and why do we use it
What is TensorFlow and why do we use it
 
error 2.pdf101316, 6(46 PM01_errorPage 1 of 5http.docx
error 2.pdf101316, 6(46 PM01_errorPage 1 of 5http.docxerror 2.pdf101316, 6(46 PM01_errorPage 1 of 5http.docx
error 2.pdf101316, 6(46 PM01_errorPage 1 of 5http.docx
 
Python seaborn cheat_sheet
Python seaborn cheat_sheetPython seaborn cheat_sheet
Python seaborn cheat_sheet
 
TypeScript and Deep Learning
TypeScript and Deep LearningTypeScript and Deep Learning
TypeScript and Deep Learning
 
Machine Learning and Go. Go!
Machine Learning and Go. Go!Machine Learning and Go. Go!
Machine Learning and Go. Go!
 
Natural language processing open seminar For Tensorflow usage
Natural language processing open seminar For Tensorflow usageNatural language processing open seminar For Tensorflow usage
Natural language processing open seminar For Tensorflow usage
 
Tensorflow
TensorflowTensorflow
Tensorflow
 
Language translation with Deep Learning (RNN) with TensorFlow
Language translation with Deep Learning (RNN) with TensorFlowLanguage translation with Deep Learning (RNN) with TensorFlow
Language translation with Deep Learning (RNN) with TensorFlow
 
Advanced Spark and TensorFlow Meetup May 26, 2016
Advanced Spark and TensorFlow Meetup May 26, 2016Advanced Spark and TensorFlow Meetup May 26, 2016
Advanced Spark and TensorFlow Meetup May 26, 2016
 
Tensorflow - Intro (2017)
Tensorflow - Intro (2017)Tensorflow - Intro (2017)
Tensorflow - Intro (2017)
 
TensorFlow example for AI Ukraine2016
TensorFlow example  for AI Ukraine2016TensorFlow example  for AI Ukraine2016
TensorFlow example for AI Ukraine2016
 
maXbox starter69 Machine Learning VII
maXbox starter69 Machine Learning VIImaXbox starter69 Machine Learning VII
maXbox starter69 Machine Learning VII
 
Deep Learning, Scala, and Spark
Deep Learning, Scala, and SparkDeep Learning, Scala, and Spark
Deep Learning, Scala, and Spark
 
Introduction to Tensor Flow for Optical Character Recognition (OCR)
Introduction to Tensor Flow for Optical Character Recognition (OCR)Introduction to Tensor Flow for Optical Character Recognition (OCR)
Introduction to Tensor Flow for Optical Character Recognition (OCR)
 

Más de Gabriel Hamilton

Javascript Smart Contracts on NEAR
Javascript Smart Contracts on NEARJavascript Smart Contracts on NEAR
Javascript Smart Contracts on NEARGabriel Hamilton
 
Natural language processing: feature extraction
Natural language processing: feature extractionNatural language processing: feature extraction
Natural language processing: feature extractionGabriel Hamilton
 
Software engineering for CEOs
Software engineering for CEOsSoftware engineering for CEOs
Software engineering for CEOsGabriel Hamilton
 
Adaptive software engineering
Adaptive software engineeringAdaptive software engineering
Adaptive software engineeringGabriel Hamilton
 
Software engineering for CEOs ch1
Software engineering for CEOs ch1Software engineering for CEOs ch1
Software engineering for CEOs ch1Gabriel Hamilton
 
DOSUG Intro to google prediction api
DOSUG Intro to google prediction apiDOSUG Intro to google prediction api
DOSUG Intro to google prediction apiGabriel Hamilton
 
How BigQuery broke my heart
How BigQuery broke my heartHow BigQuery broke my heart
How BigQuery broke my heartGabriel Hamilton
 
How to present lots of information on a screen
How to present lots of information on a screenHow to present lots of information on a screen
How to present lots of information on a screenGabriel Hamilton
 
Intro to Google Prediction API
Intro to Google Prediction APIIntro to Google Prediction API
Intro to Google Prediction APIGabriel Hamilton
 
Dojo: Beautiful Web Apps, Fast
Dojo: Beautiful Web Apps, FastDojo: Beautiful Web Apps, Fast
Dojo: Beautiful Web Apps, FastGabriel Hamilton
 
Dojo: Getting Started Today
Dojo: Getting Started TodayDojo: Getting Started Today
Dojo: Getting Started TodayGabriel Hamilton
 

Más de Gabriel Hamilton (15)

Javascript Smart Contracts on NEAR
Javascript Smart Contracts on NEARJavascript Smart Contracts on NEAR
Javascript Smart Contracts on NEAR
 
Smart Contracts
Smart ContractsSmart Contracts
Smart Contracts
 
Web Next
Web NextWeb Next
Web Next
 
Beyond Agile Software
Beyond Agile SoftwareBeyond Agile Software
Beyond Agile Software
 
Natural language processing: feature extraction
Natural language processing: feature extractionNatural language processing: feature extraction
Natural language processing: feature extraction
 
Software engineering for CEOs
Software engineering for CEOsSoftware engineering for CEOs
Software engineering for CEOs
 
Adaptive software engineering
Adaptive software engineeringAdaptive software engineering
Adaptive software engineering
 
DataFlow & Beam
DataFlow & BeamDataFlow & Beam
DataFlow & Beam
 
Software engineering for CEOs ch1
Software engineering for CEOs ch1Software engineering for CEOs ch1
Software engineering for CEOs ch1
 
DOSUG Intro to google prediction api
DOSUG Intro to google prediction apiDOSUG Intro to google prediction api
DOSUG Intro to google prediction api
 
How BigQuery broke my heart
How BigQuery broke my heartHow BigQuery broke my heart
How BigQuery broke my heart
 
How to present lots of information on a screen
How to present lots of information on a screenHow to present lots of information on a screen
How to present lots of information on a screen
 
Intro to Google Prediction API
Intro to Google Prediction APIIntro to Google Prediction API
Intro to Google Prediction API
 
Dojo: Beautiful Web Apps, Fast
Dojo: Beautiful Web Apps, FastDojo: Beautiful Web Apps, Fast
Dojo: Beautiful Web Apps, Fast
 
Dojo: Getting Started Today
Dojo: Getting Started TodayDojo: Getting Started Today
Dojo: Getting Started Today
 

Último

MYjobs Presentation Django-based project
MYjobs Presentation Django-based projectMYjobs Presentation Django-based project
MYjobs Presentation Django-based projectAnoyGreter
 
What is Advanced Excel and what are some best practices for designing and cre...
What is Advanced Excel and what are some best practices for designing and cre...What is Advanced Excel and what are some best practices for designing and cre...
What is Advanced Excel and what are some best practices for designing and cre...Technogeeks
 
Intelligent Home Wi-Fi Solutions | ThinkPalm
Intelligent Home Wi-Fi Solutions | ThinkPalmIntelligent Home Wi-Fi Solutions | ThinkPalm
Intelligent Home Wi-Fi Solutions | ThinkPalmSujith Sukumaran
 
Innovate and Collaborate- Harnessing the Power of Open Source Software.pdf
Innovate and Collaborate- Harnessing the Power of Open Source Software.pdfInnovate and Collaborate- Harnessing the Power of Open Source Software.pdf
Innovate and Collaborate- Harnessing the Power of Open Source Software.pdfYashikaSharma391629
 
Simplifying Microservices & Apps - The art of effortless development - Meetup...
Simplifying Microservices & Apps - The art of effortless development - Meetup...Simplifying Microservices & Apps - The art of effortless development - Meetup...
Simplifying Microservices & Apps - The art of effortless development - Meetup...Rob Geurden
 
React Server Component in Next.js by Hanief Utama
React Server Component in Next.js by Hanief UtamaReact Server Component in Next.js by Hanief Utama
React Server Component in Next.js by Hanief UtamaHanief Utama
 
Folding Cheat Sheet #4 - fourth in a series
Folding Cheat Sheet #4 - fourth in a seriesFolding Cheat Sheet #4 - fourth in a series
Folding Cheat Sheet #4 - fourth in a seriesPhilip Schwarz
 
Cyber security and its impact on E commerce
Cyber security and its impact on E commerceCyber security and its impact on E commerce
Cyber security and its impact on E commercemanigoyal112
 
Taming Distributed Systems: Key Insights from Wix's Large-Scale Experience - ...
Taming Distributed Systems: Key Insights from Wix's Large-Scale Experience - ...Taming Distributed Systems: Key Insights from Wix's Large-Scale Experience - ...
Taming Distributed Systems: Key Insights from Wix's Large-Scale Experience - ...Natan Silnitsky
 
Call Us🔝>༒+91-9711147426⇛Call In girls karol bagh (Delhi)
Call Us🔝>༒+91-9711147426⇛Call In girls karol bagh (Delhi)Call Us🔝>༒+91-9711147426⇛Call In girls karol bagh (Delhi)
Call Us🔝>༒+91-9711147426⇛Call In girls karol bagh (Delhi)jennyeacort
 
Open Source Summit NA 2024: Open Source Cloud Costs - OpenCost's Impact on En...
Open Source Summit NA 2024: Open Source Cloud Costs - OpenCost's Impact on En...Open Source Summit NA 2024: Open Source Cloud Costs - OpenCost's Impact on En...
Open Source Summit NA 2024: Open Source Cloud Costs - OpenCost's Impact on En...Matt Ray
 
VK Business Profile - provides IT solutions and Web Development
VK Business Profile - provides IT solutions and Web DevelopmentVK Business Profile - provides IT solutions and Web Development
VK Business Profile - provides IT solutions and Web Developmentvyaparkranti
 
Xen Safety Embedded OSS Summit April 2024 v4.pdf
Xen Safety Embedded OSS Summit April 2024 v4.pdfXen Safety Embedded OSS Summit April 2024 v4.pdf
Xen Safety Embedded OSS Summit April 2024 v4.pdfStefano Stabellini
 
SpotFlow: Tracking Method Calls and States at Runtime
SpotFlow: Tracking Method Calls and States at RuntimeSpotFlow: Tracking Method Calls and States at Runtime
SpotFlow: Tracking Method Calls and States at Runtimeandrehoraa
 
Cloud Data Center Network Construction - IEEE
Cloud Data Center Network Construction - IEEECloud Data Center Network Construction - IEEE
Cloud Data Center Network Construction - IEEEVICTOR MAESTRE RAMIREZ
 
Odoo 14 - eLearning Module In Odoo 14 Enterprise
Odoo 14 - eLearning Module In Odoo 14 EnterpriseOdoo 14 - eLearning Module In Odoo 14 Enterprise
Odoo 14 - eLearning Module In Odoo 14 Enterprisepreethippts
 
Ahmed Motair CV April 2024 (Senior SW Developer)
Ahmed Motair CV April 2024 (Senior SW Developer)Ahmed Motair CV April 2024 (Senior SW Developer)
Ahmed Motair CV April 2024 (Senior SW Developer)Ahmed Mater
 
Dealing with Cultural Dispersion — Stefano Lambiase — ICSE-SEIS 2024
Dealing with Cultural Dispersion — Stefano Lambiase — ICSE-SEIS 2024Dealing with Cultural Dispersion — Stefano Lambiase — ICSE-SEIS 2024
Dealing with Cultural Dispersion — Stefano Lambiase — ICSE-SEIS 2024StefanoLambiase
 
Unveiling the Future: Sylius 2.0 New Features
Unveiling the Future: Sylius 2.0 New FeaturesUnveiling the Future: Sylius 2.0 New Features
Unveiling the Future: Sylius 2.0 New FeaturesŁukasz Chruściel
 
Powering Real-Time Decisions with Continuous Data Streams
Powering Real-Time Decisions with Continuous Data StreamsPowering Real-Time Decisions with Continuous Data Streams
Powering Real-Time Decisions with Continuous Data StreamsSafe Software
 

Último (20)

MYjobs Presentation Django-based project
MYjobs Presentation Django-based projectMYjobs Presentation Django-based project
MYjobs Presentation Django-based project
 
What is Advanced Excel and what are some best practices for designing and cre...
What is Advanced Excel and what are some best practices for designing and cre...What is Advanced Excel and what are some best practices for designing and cre...
What is Advanced Excel and what are some best practices for designing and cre...
 
Intelligent Home Wi-Fi Solutions | ThinkPalm
Intelligent Home Wi-Fi Solutions | ThinkPalmIntelligent Home Wi-Fi Solutions | ThinkPalm
Intelligent Home Wi-Fi Solutions | ThinkPalm
 
Innovate and Collaborate- Harnessing the Power of Open Source Software.pdf
Innovate and Collaborate- Harnessing the Power of Open Source Software.pdfInnovate and Collaborate- Harnessing the Power of Open Source Software.pdf
Innovate and Collaborate- Harnessing the Power of Open Source Software.pdf
 
Simplifying Microservices & Apps - The art of effortless development - Meetup...
Simplifying Microservices & Apps - The art of effortless development - Meetup...Simplifying Microservices & Apps - The art of effortless development - Meetup...
Simplifying Microservices & Apps - The art of effortless development - Meetup...
 
React Server Component in Next.js by Hanief Utama
React Server Component in Next.js by Hanief UtamaReact Server Component in Next.js by Hanief Utama
React Server Component in Next.js by Hanief Utama
 
Folding Cheat Sheet #4 - fourth in a series
Folding Cheat Sheet #4 - fourth in a seriesFolding Cheat Sheet #4 - fourth in a series
Folding Cheat Sheet #4 - fourth in a series
 
Cyber security and its impact on E commerce
Cyber security and its impact on E commerceCyber security and its impact on E commerce
Cyber security and its impact on E commerce
 
Taming Distributed Systems: Key Insights from Wix's Large-Scale Experience - ...
Taming Distributed Systems: Key Insights from Wix's Large-Scale Experience - ...Taming Distributed Systems: Key Insights from Wix's Large-Scale Experience - ...
Taming Distributed Systems: Key Insights from Wix's Large-Scale Experience - ...
 
Call Us🔝>༒+91-9711147426⇛Call In girls karol bagh (Delhi)
Call Us🔝>༒+91-9711147426⇛Call In girls karol bagh (Delhi)Call Us🔝>༒+91-9711147426⇛Call In girls karol bagh (Delhi)
Call Us🔝>༒+91-9711147426⇛Call In girls karol bagh (Delhi)
 
Open Source Summit NA 2024: Open Source Cloud Costs - OpenCost's Impact on En...
Open Source Summit NA 2024: Open Source Cloud Costs - OpenCost's Impact on En...Open Source Summit NA 2024: Open Source Cloud Costs - OpenCost's Impact on En...
Open Source Summit NA 2024: Open Source Cloud Costs - OpenCost's Impact on En...
 
VK Business Profile - provides IT solutions and Web Development
VK Business Profile - provides IT solutions and Web DevelopmentVK Business Profile - provides IT solutions and Web Development
VK Business Profile - provides IT solutions and Web Development
 
Xen Safety Embedded OSS Summit April 2024 v4.pdf
Xen Safety Embedded OSS Summit April 2024 v4.pdfXen Safety Embedded OSS Summit April 2024 v4.pdf
Xen Safety Embedded OSS Summit April 2024 v4.pdf
 
SpotFlow: Tracking Method Calls and States at Runtime
SpotFlow: Tracking Method Calls and States at RuntimeSpotFlow: Tracking Method Calls and States at Runtime
SpotFlow: Tracking Method Calls and States at Runtime
 
Cloud Data Center Network Construction - IEEE
Cloud Data Center Network Construction - IEEECloud Data Center Network Construction - IEEE
Cloud Data Center Network Construction - IEEE
 
Odoo 14 - eLearning Module In Odoo 14 Enterprise
Odoo 14 - eLearning Module In Odoo 14 EnterpriseOdoo 14 - eLearning Module In Odoo 14 Enterprise
Odoo 14 - eLearning Module In Odoo 14 Enterprise
 
Ahmed Motair CV April 2024 (Senior SW Developer)
Ahmed Motair CV April 2024 (Senior SW Developer)Ahmed Motair CV April 2024 (Senior SW Developer)
Ahmed Motair CV April 2024 (Senior SW Developer)
 
Dealing with Cultural Dispersion — Stefano Lambiase — ICSE-SEIS 2024
Dealing with Cultural Dispersion — Stefano Lambiase — ICSE-SEIS 2024Dealing with Cultural Dispersion — Stefano Lambiase — ICSE-SEIS 2024
Dealing with Cultural Dispersion — Stefano Lambiase — ICSE-SEIS 2024
 
Unveiling the Future: Sylius 2.0 New Features
Unveiling the Future: Sylius 2.0 New FeaturesUnveiling the Future: Sylius 2.0 New Features
Unveiling the Future: Sylius 2.0 New Features
 
Powering Real-Time Decisions with Continuous Data Streams
Powering Real-Time Decisions with Continuous Data StreamsPowering Real-Time Decisions with Continuous Data Streams
Powering Real-Time Decisions with Continuous Data Streams
 

The TensorFlow dance craze

  • 2. TensorFlow is a Machine Learning library
  • 3. What is Machine Learning? usually: Statistical Pattern Matching Using past measurements to predict something about a new piece of information
  • 4. Does this picture contain a cat? Classification How much is this home worth? Regression Regression Talk https://docs.google.com/presentation/d/17FoojZ17DKDZqoByhB16PmtAXtnJ tXSy1-feK9-A_fg/edit#slide=id.p10
  • 5. There are lots of other ML libraries
  • 6. Is it right for you? Maybe Not, use Prediction API http://www.slideshare.net/gabehamilton/intro-to-google-prediction-api-15167420 Or equivalent Amazon or Microsoft APIs if you have a CSV of observed data.
  • 7. But I’d like to get into the details or I am working on a complex problem...
  • 8. You do still have some choices. Some people prefer Keras on top of TensorFlow https://keras.io/ or tf-slim or pretty-tensor
  • 9. So why use TensorFlow? It’s not much different than the “easier” libraries. You’ll want to understand more and more details anyway. Because you like It has the hottest dance moves!
  • 10. Look out a Tensor!
  • 11. Some Math and a Multi-Dimensional Array had a baby
  • 12. For our purposes It’s a multi-dimensional array. Just remember that you are putting a mathematical construct in that array. A tensor is a multi-dimensional array with certain transformation properties
  • 13. You have some data Even though it’s in a 2D spreadsheet it can describe a multidimensional space. House Price Data 1 mile to park 2 bedrooms 1800 sq ft So our Tensor is [1, 2, 1800]Square footage Distance to park # of bathrooms
  • 14. Let’s build a Tensor Machine = a Tensor
  • 15. Comparing output is our Output But we are expecting - = Loss
  • 16. Iterate until we have a good model
  • 19. Demo code: fitting a line to points Demo is of Datalab notebook # Create 100 phony x, y data points in NumPy, y = x * 0.1 + 0.3 tf.reset_default_graph() import numpy as np import matplotlib.pyplot as plt %matplotlib inline x_measured = np.random.rand(100).astype(np.float32) y_measured = x_measured * (0.1 + (0.05 *np.random.rand(100))) + 0.3 plt.scatter(x_measured, y_measured) plt.xlabel('<- Bluer : Uniform Color : Redder ->') plt.ylabel('Deaths per mission') plt.title('Star Trek Uniform Color Mortality Incidence') # plt.plot([0, 1], [0, 0.5], color='purple', lw=2) # plt.plot([0, 1], [0.25, 0.5], color='purple', lw=2) Measured Data
  • 20. Demo code continued import tensorflow as tf # Try to find values for slope and offset that match # y_measured = slope * x_measured + offset slope = tf.Variable(tf.random_uniform([1], -1.0, 1.0)) offset = tf.Variable(tf.zeros([1])) y_predicted = slope * x_measured + offset loss = tf.reduce_mean(tf.square(y_predicted - y_measured)) optimizer = tf.train.GradientDescentOptimizer(0.5) train = optimizer.minimize(loss) A test value for slope
  • 21. Demo code continued # Launch the graph. sess = tf.Session() sess.run(tf.initialize_all_variables()) # and initialize variables # Fit the line. print 'step #t', 'slopett', 'offset' for step in range(201): sess.run(train) if step % 20 == 0: print step,'t', sess.run(slope)[0], 't', sess.run(offset)[0] A test value for slope and offset
  • 22. Q & A Plus more slides for longer talks or answering questions
  • 23. Why TensorFlow is useful Build your graph in a high level language, execute in fast implementations. Distribute graph operations across processors. Whole graph can be optimized.
  • 24. 4+ D Spaces A given measurement all fits into a simple Tensor: [4, 4, 4, 3]
  • 25. Some Tensors Scalar 0.2 Vector [1, 2, 1800] Matrix [2, 1, 1], [1, 2, 0], [0, 1, 0] n-Tensors
  • 26. Rank 2 Tensor When a bunch of vectors hang out they make a Matrix [2, 1, 1], [1, 2, 0], [0, 1, 0]