SlideShare a Scribd company logo
1 of 18
Download to read offline
Hacker’s Guide to Neural Networks
a. k. a.
Data Driven Code – 101
Anoop Thomas Mathew
@atmb4u
PyCon Canada 2016
WHAT WE WILL NOT COVER
• Recent developments in
• United States of America! ;)
• Deep Learning, CNN, RNN, DCGAN etc.
• Frameworks like TensorFlow, Theano, Keras etc.
• Advanced concepts of neural networks
WHAT WE WILL COVER
• Basic Concepts of
• Parameter Optimization
• Entropy (Sparse Coding)
• Little bit of Mathematics
• Linear Algebra – Matrix Multiplication
• Differential Calculus – Sigmoid Function (2 equations only)
• (Try to) Build a 2 layer neural network
• Way Forward
PARAMETER OPTIMIZATION
• Infinite Monkey Theorem
• Any problem is fundamentally a parameter optimization problem
𝑎𝑥3 + 𝑏𝑥2 + 𝑐𝑥 + 𝑑 = 0
0/1
noise bit
data bits
28 = 256
Imagine:
• divided into 4 spaces
• each bit – a feature
• generalize data bits
• attenuates noise bit
ENTROPY
0/1
0/1
• Sparse Coding
LITTLE LINEAR ALGEBRA
𝑤1 𝑤2
𝑤3 𝑤4
×
𝑥1
𝑥2
=
𝑤1 𝑥1 + 𝑤2 𝑥2
𝑤3 𝑥1 + 𝑤4 𝑥2
LITTLE LINEAR ALGEBRA (matrix multiplication)
𝑤1 𝑤2
𝑤3 𝑤4
×
𝑥1
𝑥2
=
𝑤1 𝑥1 + 𝑤2 𝑥2
𝑤3 𝑥1 + 𝑤4 𝑥2
ACTIVATION FUNCTION (differential calculus part)
σ(x) =
/
1+e−x
(Sigmoid Function)
0	∂σ(x)
02
= σ(x)	×	(1−σ(x))
(Derivative of Sigmoid Function)
Stochastic Gradient Decent
QUICK RECAP
• Activation Function(combining inputs to a representation)
• Layers (Weight Matrices)
• Network (collection of weight matrices)
• Dataset (inputs and expect outputs)
• Features (patterns in dataset)
• Sparse Encoding (roomfor error)
• Backpropagation (learn from past mistakes)
• Parameter Optimization (correct values into weight matrix)
LET’S MAKE ONE NOW !
CODE + DATA = MAGIC
(Teach machine XOR truth table)
XOR GATE
SHOW ME THE
CODE
DEEP LEARNING
DEEP LEARNING
WAY FORWARD
Play with Neural networks in the browser
http://playground.tensorflow.org/
Comprehensive list of resources available online on Deep Learning
https://github.com/ChristosChristofidis/awesome-deep-learning
Very active online Machine Learning Community
https://www.kaggle.com/
REFERENCE LINKS / IMAGE COURTESY
• https://medium.com/technology-invention-and-more/how-to-build-a-simple-
neural-network-in-9-lines-of-python-code-cc8f23647ca1
• https://medium.com/technology-invention-and-more/how-to-build-a-multi-
layered-neural-network-in-python-53ec3d1d326a#.dis92by0e
• http://iamtrask.github.io/2015/07/12/basic-python-network/
• http://iamtrask.github.io/2015/07/27/python-network-part2/
• http://sebastianraschka.com/faq/docs/logisticregr-neuralnet.html
THANK YOU
// atm@infiniteloop.in
• Code - https://github.com/atmb4u/data-driven-code
• Slides – https://slideshare.net/atmb4u/data-driven-code
• Medium - https://medium.com/@atmb4u/data-driven-code-101-17003f7b88ec

More Related Content

What's hot

Dr. Erin LeDell, Machine Learning Scientist, H2O.ai at MLconf SEA - 5/20/16
Dr. Erin LeDell, Machine Learning Scientist, H2O.ai at MLconf SEA - 5/20/16Dr. Erin LeDell, Machine Learning Scientist, H2O.ai at MLconf SEA - 5/20/16
Dr. Erin LeDell, Machine Learning Scientist, H2O.ai at MLconf SEA - 5/20/16
MLconf
 

What's hot (20)

Data Science at the Command Line
Data Science at the Command LineData Science at the Command Line
Data Science at the Command Line
 
Introduction to Neural Networks and Deep Learning
Introduction to Neural Networks and Deep LearningIntroduction to Neural Networks and Deep Learning
Introduction to Neural Networks and Deep Learning
 
Sergei Vassilvitskii, Research Scientist, Google at MLconf NYC - 4/15/16
Sergei Vassilvitskii, Research Scientist, Google at MLconf NYC - 4/15/16Sergei Vassilvitskii, Research Scientist, Google at MLconf NYC - 4/15/16
Sergei Vassilvitskii, Research Scientist, Google at MLconf NYC - 4/15/16
 
How to win data science competitions with Deep Learning
How to win data science competitions with Deep LearningHow to win data science competitions with Deep Learning
How to win data science competitions with Deep Learning
 
TensorFrames: Google Tensorflow on Apache Spark
TensorFrames: Google Tensorflow on Apache SparkTensorFrames: Google Tensorflow on Apache Spark
TensorFrames: Google Tensorflow on Apache Spark
 
Distributed implementation of a lstm on spark and tensorflow
Distributed implementation of a lstm on spark and tensorflowDistributed implementation of a lstm on spark and tensorflow
Distributed implementation of a lstm on spark and tensorflow
 
Dr. Erin LeDell, Machine Learning Scientist, H2O.ai at MLconf SEA - 5/20/16
Dr. Erin LeDell, Machine Learning Scientist, H2O.ai at MLconf SEA - 5/20/16Dr. Erin LeDell, Machine Learning Scientist, H2O.ai at MLconf SEA - 5/20/16
Dr. Erin LeDell, Machine Learning Scientist, H2O.ai at MLconf SEA - 5/20/16
 
Polyglot Persistence in the Real World: Cassandra + S3 + MapReduce
Polyglot Persistence in the Real World: Cassandra + S3 + MapReducePolyglot Persistence in the Real World: Cassandra + S3 + MapReduce
Polyglot Persistence in the Real World: Cassandra + S3 + MapReduce
 
Digit recognizer by convolutional neural network
Digit recognizer by convolutional neural networkDigit recognizer by convolutional neural network
Digit recognizer by convolutional neural network
 
PyData NYC: Build an AI-powered Pet Detector with Visual Studio Code
PyData NYC: Build an AI-powered Pet Detector with Visual Studio Code PyData NYC: Build an AI-powered Pet Detector with Visual Studio Code
PyData NYC: Build an AI-powered Pet Detector with Visual Studio Code
 
Alex Smola, Professor in the Machine Learning Department, Carnegie Mellon Uni...
Alex Smola, Professor in the Machine Learning Department, Carnegie Mellon Uni...Alex Smola, Professor in the Machine Learning Department, Carnegie Mellon Uni...
Alex Smola, Professor in the Machine Learning Department, Carnegie Mellon Uni...
 
Neural networks and google tensor flow
Neural networks and google tensor flowNeural networks and google tensor flow
Neural networks and google tensor flow
 
Bubble Sort algorithm in Assembly Language
Bubble Sort algorithm in Assembly LanguageBubble Sort algorithm in Assembly Language
Bubble Sort algorithm in Assembly Language
 
Using sage maths to solve systems of linear equations
Using sage maths to solve systems of linear equationsUsing sage maths to solve systems of linear equations
Using sage maths to solve systems of linear equations
 
Applying your Convolutional Neural Networks
Applying your Convolutional Neural NetworksApplying your Convolutional Neural Networks
Applying your Convolutional Neural Networks
 
AlphaGo Zero: Mastering the Game of Go Without Human Knowledge
AlphaGo Zero: Mastering the Game of Go Without Human KnowledgeAlphaGo Zero: Mastering the Game of Go Without Human Knowledge
AlphaGo Zero: Mastering the Game of Go Without Human Knowledge
 
Introduction to Deep Learning with TensorFlow
Introduction to Deep Learning with TensorFlowIntroduction to Deep Learning with TensorFlow
Introduction to Deep Learning with TensorFlow
 
Neural Network with Python & TensorFlow
Neural Network with Python & TensorFlowNeural Network with Python & TensorFlow
Neural Network with Python & TensorFlow
 
Quantum programming in a nutshell
 Quantum programming in a nutshell Quantum programming in a nutshell
Quantum programming in a nutshell
 
Parallel Recurrent Neural Network Architectures for Feature-rich Session-base...
Parallel Recurrent Neural Network Architectures for Feature-rich Session-base...Parallel Recurrent Neural Network Architectures for Feature-rich Session-base...
Parallel Recurrent Neural Network Architectures for Feature-rich Session-base...
 

Viewers also liked

Viewers also liked (20)

Thinking in Functions: Functional Programming in Python
Thinking in Functions: Functional Programming in PythonThinking in Functions: Functional Programming in Python
Thinking in Functions: Functional Programming in Python
 
Writing Smarter Applications with Machine Learning
Writing Smarter Applications with Machine LearningWriting Smarter Applications with Machine Learning
Writing Smarter Applications with Machine Learning
 
ingenium
ingeniumingenium
ingenium
 
Protoyping Painkiller Startups
Protoyping Painkiller StartupsProtoyping Painkiller Startups
Protoyping Painkiller Startups
 
Word Dictionary - Software Development Project 1
Word Dictionary - Software Development Project 1 Word Dictionary - Software Development Project 1
Word Dictionary - Software Development Project 1
 
Python 101
Python 101Python 101
Python 101
 
Python in-the-enterprise-brochure
Python in-the-enterprise-brochurePython in-the-enterprise-brochure
Python in-the-enterprise-brochure
 
Web Development Fundamentals
Web Development FundamentalsWeb Development Fundamentals
Web Development Fundamentals
 
Cross Cultural Communication
Cross Cultural CommunicationCross Cultural Communication
Cross Cultural Communication
 
Python Programming - I. Introduction
Python Programming - I. IntroductionPython Programming - I. Introduction
Python Programming - I. Introduction
 
Presentation on mini dictionary using C language
Presentation on  mini dictionary using C languagePresentation on  mini dictionary using C language
Presentation on mini dictionary using C language
 
Digital life ppt 2
Digital life ppt 2Digital life ppt 2
Digital life ppt 2
 
Aktuelle Entwicklungen in der Lebensmittelindustrie und ihre Auswirkungen auf...
Aktuelle Entwicklungen in der Lebensmittelindustrie und ihre Auswirkungen auf...Aktuelle Entwicklungen in der Lebensmittelindustrie und ihre Auswirkungen auf...
Aktuelle Entwicklungen in der Lebensmittelindustrie und ihre Auswirkungen auf...
 
Make In India: a presentation openly ended for its Unlimited Applications
Make In India: a presentation openly ended for its Unlimited ApplicationsMake In India: a presentation openly ended for its Unlimited Applications
Make In India: a presentation openly ended for its Unlimited Applications
 
Python Programming - V. Sequences (List and Tuples) and Dictionaries
Python Programming - V. Sequences (List and Tuples) and DictionariesPython Programming - V. Sequences (List and Tuples) and Dictionaries
Python Programming - V. Sequences (List and Tuples) and Dictionaries
 
Dictionary ppt
Dictionary pptDictionary ppt
Dictionary ppt
 
PPt With animation on Mera Digital India
PPt With animation on Mera Digital IndiaPPt With animation on Mera Digital India
PPt With animation on Mera Digital India
 
A 12 hour workshop on Introduction to Python
A 12 hour workshop on Introduction to PythonA 12 hour workshop on Introduction to Python
A 12 hour workshop on Introduction to Python
 
Digital strategy for a successful smart city initiative
Digital strategy for a successful smart city initiativeDigital strategy for a successful smart city initiative
Digital strategy for a successful smart city initiative
 
The Dictionary Project
The Dictionary ProjectThe Dictionary Project
The Dictionary Project
 

Similar to Data Driven Code

Deep Recurrent Neural Networks for Sequence Learning in Spark by Yves Mabiala
Deep Recurrent Neural Networks for Sequence Learning in Spark by Yves MabialaDeep Recurrent Neural Networks for Sequence Learning in Spark by Yves Mabiala
Deep Recurrent Neural Networks for Sequence Learning in Spark by Yves Mabiala
Spark Summit
 
Separating Hype from Reality in Deep Learning with Sameer Farooqui
 Separating Hype from Reality in Deep Learning with Sameer Farooqui Separating Hype from Reality in Deep Learning with Sameer Farooqui
Separating Hype from Reality in Deep Learning with Sameer Farooqui
Databricks
 

Similar to Data Driven Code (20)

Deep learning with TensorFlow
Deep learning with TensorFlowDeep learning with TensorFlow
Deep learning with TensorFlow
 
Hardware Acceleration for Machine Learning
Hardware Acceleration for Machine LearningHardware Acceleration for Machine Learning
Hardware Acceleration for Machine Learning
 
Writing Fast MATLAB Code
Writing Fast MATLAB CodeWriting Fast MATLAB Code
Writing Fast MATLAB Code
 
Deep Feed Forward Neural Networks and Regularization
Deep Feed Forward Neural Networks and RegularizationDeep Feed Forward Neural Networks and Regularization
Deep Feed Forward Neural Networks and Regularization
 
Haskell for data science
Haskell for data scienceHaskell for data science
Haskell for data science
 
Machine Learning on Azure - AzureConf
Machine Learning on Azure - AzureConfMachine Learning on Azure - AzureConf
Machine Learning on Azure - AzureConf
 
Multilayer Perceptron - Elisa Sayrol - UPC Barcelona 2018
Multilayer Perceptron - Elisa Sayrol - UPC Barcelona 2018Multilayer Perceptron - Elisa Sayrol - UPC Barcelona 2018
Multilayer Perceptron - Elisa Sayrol - UPC Barcelona 2018
 
Machine Learning in Action
Machine Learning in ActionMachine Learning in Action
Machine Learning in Action
 
Understanding Basics of Machine Learning
Understanding Basics of Machine LearningUnderstanding Basics of Machine Learning
Understanding Basics of Machine Learning
 
Deep learning from scratch
Deep learning from scratch Deep learning from scratch
Deep learning from scratch
 
DeepLearningLecture.pptx
DeepLearningLecture.pptxDeepLearningLecture.pptx
DeepLearningLecture.pptx
 
Scalable Deep Learning Using Apache MXNet
Scalable Deep Learning Using Apache MXNetScalable Deep Learning Using Apache MXNet
Scalable Deep Learning Using Apache MXNet
 
Deep Recurrent Neural Networks for Sequence Learning in Spark by Yves Mabiala
Deep Recurrent Neural Networks for Sequence Learning in Spark by Yves MabialaDeep Recurrent Neural Networks for Sequence Learning in Spark by Yves Mabiala
Deep Recurrent Neural Networks for Sequence Learning in Spark by Yves Mabiala
 
Lec3
Lec3Lec3
Lec3
 
Modern classification techniques
Modern classification techniquesModern classification techniques
Modern classification techniques
 
Hadoop Summit 2012 | Bayesian Counters AKA In Memory Data Mining for Large Da...
Hadoop Summit 2012 | Bayesian Counters AKA In Memory Data Mining for Large Da...Hadoop Summit 2012 | Bayesian Counters AKA In Memory Data Mining for Large Da...
Hadoop Summit 2012 | Bayesian Counters AKA In Memory Data Mining for Large Da...
 
Meetup Julio Algoritmos Genéticos
Meetup Julio Algoritmos GenéticosMeetup Julio Algoritmos Genéticos
Meetup Julio Algoritmos Genéticos
 
Presentation on machine learning
Presentation on machine learningPresentation on machine learning
Presentation on machine learning
 
Beating Floating Point at its Own Game: Posit Arithmetic
Beating Floating Point at its Own Game: Posit ArithmeticBeating Floating Point at its Own Game: Posit Arithmetic
Beating Floating Point at its Own Game: Posit Arithmetic
 
Separating Hype from Reality in Deep Learning with Sameer Farooqui
 Separating Hype from Reality in Deep Learning with Sameer Farooqui Separating Hype from Reality in Deep Learning with Sameer Farooqui
Separating Hype from Reality in Deep Learning with Sameer Farooqui
 

More from Anoop Thomas Mathew

Test Driven Development in Python
Test Driven Development in PythonTest Driven Development in Python
Test Driven Development in Python
Anoop Thomas Mathew
 

More from Anoop Thomas Mathew (13)

What The Web!
What The Web!What The Web!
What The Web!
 
Investor pitch deck for Vibe
Investor pitch deck for VibeInvestor pitch deck for Vibe
Investor pitch deck for Vibe
 
Getting Started on distributed version control with git
Getting Started on distributed version control with gitGetting Started on distributed version control with git
Getting Started on distributed version control with git
 
Let's Contribute
Let's ContributeLet's Contribute
Let's Contribute
 
Advanced Computing for Sustainable Future
Advanced Computing for Sustainable FutureAdvanced Computing for Sustainable Future
Advanced Computing for Sustainable Future
 
Ambidextrous Python - Introduction Python Libraries
Ambidextrous Python - Introduction Python Libraries Ambidextrous Python - Introduction Python Libraries
Ambidextrous Python - Introduction Python Libraries
 
Faster Python
Faster PythonFaster Python
Faster Python
 
Startups and FOSS
Startups and FOSSStartups and FOSS
Startups and FOSS
 
How slow is Real slow - PyCon India 2013
How slow is Real slow - PyCon India 2013 How slow is Real slow - PyCon India 2013
How slow is Real slow - PyCon India 2013
 
Redis way of Anayltics with Python - Fifth Elephant 2012
Redis way of Anayltics with Python - Fifth Elephant 2012Redis way of Anayltics with Python - Fifth Elephant 2012
Redis way of Anayltics with Python - Fifth Elephant 2012
 
Building a Company atop of Open Source
Building a Company atop of Open SourceBuilding a Company atop of Open Source
Building a Company atop of Open Source
 
Pycon 2012 Scikit-Learn
Pycon 2012 Scikit-LearnPycon 2012 Scikit-Learn
Pycon 2012 Scikit-Learn
 
Test Driven Development in Python
Test Driven Development in PythonTest Driven Development in Python
Test Driven Development in Python
 

Recently uploaded

Activity Planning: Objectives, Project Schedule, Network Planning Model. Time...
Activity Planning: Objectives, Project Schedule, Network Planning Model. Time...Activity Planning: Objectives, Project Schedule, Network Planning Model. Time...
Activity Planning: Objectives, Project Schedule, Network Planning Model. Time...
Lovely Professional University
 
Teachers record management system project report..pdf
Teachers record management system project report..pdfTeachers record management system project report..pdf
Teachers record management system project report..pdf
Kamal Acharya
 
School management system project report.pdf
School management system project report.pdfSchool management system project report.pdf
School management system project report.pdf
Kamal Acharya
 
DR PROF ING GURUDUTT SAHNI WIKIPEDIA.pdf
DR PROF ING GURUDUTT SAHNI WIKIPEDIA.pdfDR PROF ING GURUDUTT SAHNI WIKIPEDIA.pdf
DR PROF ING GURUDUTT SAHNI WIKIPEDIA.pdf
DrGurudutt
 
Complex plane, Modulus, Argument, Graphical representation of a complex numbe...
Complex plane, Modulus, Argument, Graphical representation of a complex numbe...Complex plane, Modulus, Argument, Graphical representation of a complex numbe...
Complex plane, Modulus, Argument, Graphical representation of a complex numbe...
MohammadAliNayeem
 

Recently uploaded (20)

Involute of a circle,Square, pentagon,HexagonInvolute_Engineering Drawing.pdf
Involute of a circle,Square, pentagon,HexagonInvolute_Engineering Drawing.pdfInvolute of a circle,Square, pentagon,HexagonInvolute_Engineering Drawing.pdf
Involute of a circle,Square, pentagon,HexagonInvolute_Engineering Drawing.pdf
 
Introduction to Machine Learning Unit-4 Notes for II-II Mechanical Engineering
Introduction to Machine Learning Unit-4 Notes for II-II Mechanical EngineeringIntroduction to Machine Learning Unit-4 Notes for II-II Mechanical Engineering
Introduction to Machine Learning Unit-4 Notes for II-II Mechanical Engineering
 
Activity Planning: Objectives, Project Schedule, Network Planning Model. Time...
Activity Planning: Objectives, Project Schedule, Network Planning Model. Time...Activity Planning: Objectives, Project Schedule, Network Planning Model. Time...
Activity Planning: Objectives, Project Schedule, Network Planning Model. Time...
 
ONLINE CAR SERVICING SYSTEM PROJECT REPORT.pdf
ONLINE CAR SERVICING SYSTEM PROJECT REPORT.pdfONLINE CAR SERVICING SYSTEM PROJECT REPORT.pdf
ONLINE CAR SERVICING SYSTEM PROJECT REPORT.pdf
 
ANSI(ST)-III_Manufacturing-I_05052020.pdf
ANSI(ST)-III_Manufacturing-I_05052020.pdfANSI(ST)-III_Manufacturing-I_05052020.pdf
ANSI(ST)-III_Manufacturing-I_05052020.pdf
 
Software Engineering - Modelling Concepts + Class Modelling + Building the An...
Software Engineering - Modelling Concepts + Class Modelling + Building the An...Software Engineering - Modelling Concepts + Class Modelling + Building the An...
Software Engineering - Modelling Concepts + Class Modelling + Building the An...
 
Arduino based vehicle speed tracker project
Arduino based vehicle speed tracker projectArduino based vehicle speed tracker project
Arduino based vehicle speed tracker project
 
Attraction and Repulsion type Moving Iron Instruments.pptx
Attraction and Repulsion type Moving Iron Instruments.pptxAttraction and Repulsion type Moving Iron Instruments.pptx
Attraction and Repulsion type Moving Iron Instruments.pptx
 
Teachers record management system project report..pdf
Teachers record management system project report..pdfTeachers record management system project report..pdf
Teachers record management system project report..pdf
 
Natalia Rutkowska - BIM School Course in Kraków
Natalia Rutkowska - BIM School Course in KrakówNatalia Rutkowska - BIM School Course in Kraków
Natalia Rutkowska - BIM School Course in Kraków
 
Multivibrator and its types defination and usges.pptx
Multivibrator and its types defination and usges.pptxMultivibrator and its types defination and usges.pptx
Multivibrator and its types defination and usges.pptx
 
Intelligent Agents, A discovery on How A Rational Agent Acts
Intelligent Agents, A discovery on How A Rational Agent ActsIntelligent Agents, A discovery on How A Rational Agent Acts
Intelligent Agents, A discovery on How A Rational Agent Acts
 
Filters for Electromagnetic Compatibility Applications
Filters for Electromagnetic Compatibility ApplicationsFilters for Electromagnetic Compatibility Applications
Filters for Electromagnetic Compatibility Applications
 
Supermarket billing system project report..pdf
Supermarket billing system project report..pdfSupermarket billing system project report..pdf
Supermarket billing system project report..pdf
 
School management system project report.pdf
School management system project report.pdfSchool management system project report.pdf
School management system project report.pdf
 
DR PROF ING GURUDUTT SAHNI WIKIPEDIA.pdf
DR PROF ING GURUDUTT SAHNI WIKIPEDIA.pdfDR PROF ING GURUDUTT SAHNI WIKIPEDIA.pdf
DR PROF ING GURUDUTT SAHNI WIKIPEDIA.pdf
 
Online book store management system project.pdf
Online book store management system project.pdfOnline book store management system project.pdf
Online book store management system project.pdf
 
BURGER ORDERING SYSYTEM PROJECT REPORT..pdf
BURGER ORDERING SYSYTEM PROJECT REPORT..pdfBURGER ORDERING SYSYTEM PROJECT REPORT..pdf
BURGER ORDERING SYSYTEM PROJECT REPORT..pdf
 
solid state electronics ktu module 5 slides
solid state electronics ktu module 5 slidessolid state electronics ktu module 5 slides
solid state electronics ktu module 5 slides
 
Complex plane, Modulus, Argument, Graphical representation of a complex numbe...
Complex plane, Modulus, Argument, Graphical representation of a complex numbe...Complex plane, Modulus, Argument, Graphical representation of a complex numbe...
Complex plane, Modulus, Argument, Graphical representation of a complex numbe...
 

Data Driven Code

  • 1. Hacker’s Guide to Neural Networks a. k. a. Data Driven Code – 101 Anoop Thomas Mathew @atmb4u PyCon Canada 2016
  • 2. WHAT WE WILL NOT COVER • Recent developments in • United States of America! ;) • Deep Learning, CNN, RNN, DCGAN etc. • Frameworks like TensorFlow, Theano, Keras etc. • Advanced concepts of neural networks
  • 3. WHAT WE WILL COVER • Basic Concepts of • Parameter Optimization • Entropy (Sparse Coding) • Little bit of Mathematics • Linear Algebra – Matrix Multiplication • Differential Calculus – Sigmoid Function (2 equations only) • (Try to) Build a 2 layer neural network • Way Forward
  • 4. PARAMETER OPTIMIZATION • Infinite Monkey Theorem • Any problem is fundamentally a parameter optimization problem 𝑎𝑥3 + 𝑏𝑥2 + 𝑐𝑥 + 𝑑 = 0
  • 5. 0/1 noise bit data bits 28 = 256 Imagine: • divided into 4 spaces • each bit – a feature • generalize data bits • attenuates noise bit ENTROPY 0/1 0/1 • Sparse Coding
  • 6. LITTLE LINEAR ALGEBRA 𝑤1 𝑤2 𝑤3 𝑤4 × 𝑥1 𝑥2 = 𝑤1 𝑥1 + 𝑤2 𝑥2 𝑤3 𝑥1 + 𝑤4 𝑥2
  • 7. LITTLE LINEAR ALGEBRA (matrix multiplication) 𝑤1 𝑤2 𝑤3 𝑤4 × 𝑥1 𝑥2 = 𝑤1 𝑥1 + 𝑤2 𝑥2 𝑤3 𝑥1 + 𝑤4 𝑥2
  • 8. ACTIVATION FUNCTION (differential calculus part) σ(x) = / 1+e−x (Sigmoid Function) 0 ∂σ(x) 02 = σ(x) × (1−σ(x)) (Derivative of Sigmoid Function) Stochastic Gradient Decent
  • 9. QUICK RECAP • Activation Function(combining inputs to a representation) • Layers (Weight Matrices) • Network (collection of weight matrices) • Dataset (inputs and expect outputs) • Features (patterns in dataset) • Sparse Encoding (roomfor error) • Backpropagation (learn from past mistakes) • Parameter Optimization (correct values into weight matrix)
  • 10. LET’S MAKE ONE NOW ! CODE + DATA = MAGIC (Teach machine XOR truth table)
  • 13.
  • 16. WAY FORWARD Play with Neural networks in the browser http://playground.tensorflow.org/ Comprehensive list of resources available online on Deep Learning https://github.com/ChristosChristofidis/awesome-deep-learning Very active online Machine Learning Community https://www.kaggle.com/
  • 17. REFERENCE LINKS / IMAGE COURTESY • https://medium.com/technology-invention-and-more/how-to-build-a-simple- neural-network-in-9-lines-of-python-code-cc8f23647ca1 • https://medium.com/technology-invention-and-more/how-to-build-a-multi- layered-neural-network-in-python-53ec3d1d326a#.dis92by0e • http://iamtrask.github.io/2015/07/12/basic-python-network/ • http://iamtrask.github.io/2015/07/27/python-network-part2/ • http://sebastianraschka.com/faq/docs/logisticregr-neuralnet.html
  • 18. THANK YOU // atm@infiniteloop.in • Code - https://github.com/atmb4u/data-driven-code • Slides – https://slideshare.net/atmb4u/data-driven-code • Medium - https://medium.com/@atmb4u/data-driven-code-101-17003f7b88ec