Automating Software Development with Deep Learning Emil Wallner, - PowerPoint PPT Presentation

Automating Software Development with Deep Learning Emil Wallner, 42, QCon São Paulo, 2019-05-7

01001001001010101010100111110110101010101000001010111010101010111101010111 00011100011011001100101010010101000101010100101010010101010100101010101010 10001010101010000000001111111010101111101000101010101010010010010010101010 10100111110110101010101000001010111010101010111101010111000111000110110011 00101010010101000101010100101010010101010100101010101010100010101010100000 00001111111010101111101000101010101010010010010010101010101001111101101010 10101000001010111010101010111101010111000111000110110011001010100101010001 01010100101010010101010100101010101010100010101010100000000011111110101011 11101000101010101010010010010010101010101001111101101010101010000010101110 10101010111101010111000111000110110011001010100101010001010101001010100101 01010100101010101010100010101010100000000011111110101011111010001010101010 10010010010010101010101001111101101010101010000010101110101010101111010101 11000111000110110011001010100101010001010101001010100101010101001010101010 10100010101010100000000011111110101011111010001010101010100100100100101010 10101001111101101010101010000010101110101010101111010101110001110001101100 11001010100101010001010101001010100101010101001010101010101000101010101000 Software Development 00000011111110101011111010001010101010100100100100101010101010011111011010 10101010000010101110101010101111010101110001110001101100110010101001010100 01010101001010100101010101001010101010101000101010101000000000111111101010 11111010001010101010100100100100101010101010011111011010101010100000101011 as Data 10101010101111010101110001110001101100110010101001010100010101010010101001 01010101001010101010101000101010101000000000111111101010111110100010101010 10100100100100101010101010011111011010101010100000101011101010101011110101 01110001110001101100110010101001010100010101010010101001010101010010101010 10101000101010101000000000111111101010111110100010101010101001001001001010 10101010011111011010101010100000101011101010101011110101011100011100011011 00110010101001010100010101010010101001010101010010101010101010001010101010 00000000111111101010111110100010101010101001001001001010101010100111110110 10101010100000101011101010101011110101011100011100011011001100101010010101 00010101010010101001010101010010101010101010001010101010000000001111111010 10111110100010101010101001001001001010101010100111110110101010101000001010 11101010101011110101011100011100011011001100101010010101000101010100101010 01010101010010101010101010001010101010000000001111111010101111101000101010 10101001001001001010101010100111110110101010101000001010111010101010111101 01011100011100011011001100101010010101000101010100101010010101010100101010 10101010001010101010000000001111111010101111101000101010101010010010010010 10101010100111110110101010101000001010111010101010111101010111000111000110

Software 1.0 - Traditional Software 2.0 - Deep learning Software 2.5 - Blended models

Source: Andrej Karpathy on Software 2.0

Software engineers are becoming data scientists

Can we automate software development 1.0 with 2.0 software?

Researchers seek to leverage their human knowledge of the domain, but the only thing that matters in the long run is the leveraging of computation. - Richard S. Sutton

2.5 2.0 1.0 Complexity

Novel Manifolds/Scalability Automation of integrated systems s m e t s y s d e s o l c f o n o i t a m o t u A Assisted Software Development Time Today

Understand an image Generate semantically correct text Correlate objects in images with text

Convolutional Neural Networks Recurrent Neural Networks Image Captioning Models

Start <HTML> <center> <H1> Hello World! </H1> </center> </HTML> End

Core structure: Pix2code (Tony Beltramelli, 2017)

Source: Thomas Leiterman using UIzard

01001001001010101010100111110110101010101000001010111010101010111101010111 00011100011011001100101010010101000101010100101010010101010100101010101010 10001010101010000000001111111010101111101000101010101010010010010010101010 10100111110110101010101000001010111010101010111101010111000111000110110011 00101010010101000101010100101010010101010100101010101010100010101010100000 00001111111010101111101000101010101010010010010010101010101001111101101010 10101000001010111010101010111101010111000111000110110011001010100101010001 01010100101010010101010100101010101010100010101010100000000011111110101011 11101000101010101010010010010010101010101001111101101010101010000010101110 10101010111101010111000111000110110011001010100101010001010101001010100101 01010100101010101010100010101010100000000011111110101011111010001010101010 10010010010010101010101001111101101010101010000010101110101010101111010101 11000111000110110011001010100101010001010101001010100101010101001010101010 10100010101010100000000011111110101011111010001010101010100100100100101010 10101001111101101010101010000010101110101010101111010101110001110001101100 11001010100101010001010101001010100101010101001010101010101000101010101000 Software Development 00000011111110101011111010001010101010100100100100101010101010011111011010 10101010000010101110101010101111010101110001110001101100110010101001010100 01010101001010100101010101001010101010101000101010101000000000111111101010 11111010001010101010100100100100101010101010011111011010101010100000101011 as Data 10101010101111010101110001110001101100110010101001010100010101010010101001 01010101001010101010101000101010101000000000111111101010111110100010101010 10100100100100101010101010011111011010101010100000101011101010101011110101 01110001110001101100110010101001010100010101010010101001010101010010101010 10101000101010101000000000111111101010111110100010101010101001001001001010 10101010011111011010101010100000101011101010101011110101011100011100011011 00110010101001010100010101010010101001010101010010101010101010001010101010 00000000111111101010111110100010101010101001001001001010101010100111110110 10101010100000101011101010101011110101011100011100011011001100101010010101 00010101010010101001010101010010101010101010001010101010000000001111111010 10111110100010101010101001001001001010101010100111110110101010101000001010 11101010101011110101011100011100011011001100101010010101000101010100101010 01010101010010101010101010001010101010000000001111111010101111101000101010 10101001001001001010101010100111110110101010101000001010111010101010111101 01011100011100011011001100101010010101000101010100101010010101010100101010 10101010001010101010000000001111111010101111101000101010101010010010010010 10101010100111110110101010101000001010111010101010111101010111000111000110

Progress Time

Image recognition Image generation Voice recognition Board games Multiplayer games Text understanding Translation Self-driving Cars Medical Image Analysis Protein Folding Handwriting Fraud detection

Progress Time

Complexity Undefined Tasks Empathy Novel Manifolds Creativity Scalability Critical thinking

2.5 2.0 1.0 Complexity

Scalability 2.5 Novel Manifolds 2.0 1.0

Augmented IDE Social Media App Bank API

Refactoring Autocomplete Code reviewing User testing GUI prototyping Semantic code search Security issues Monitoring

Scalable Novel Manifolds

Dynamic pages Linking pages Using Variables Security Rules Integrating databases

API roles Transactions ATM integrations Communication World Model Deep Security Troubleshooting

Systems of A program Functions Programs A document Paragraphs Documents Dynamic GUI Static GUI Advanced GUIs Conversations Short Conversations Expert-level with context Dialogs

emilwallner (github/twitter) w@llner.co

Automating Software Development with Deep Learning Emil Wallner, - PowerPoint PPT Presentation

Automating Software Development with Deep Learning Emil Wallner, 42, QCon So Paulo, 2019-05-7 01001001001010101010100111110110101010101000001010111010101010111101010111

1 Automating Machine Learning and Deep Learning Workflows 2 Information Name: Mourad

Automating Operations with Machine Learning Matt Callanan Senior Software Development Engineer

Automating High-Content Screening Image Analysis with Deep Learning GPU Technology Conference

Automating Cloud Deployment for Deep Learning Inference of Real-time Online Services Yang Li

N. Lane et al. l. DeepX: A Software Accelerator for Low Power Deep Learning In Inference on

Deep Learning Robot Demo - ROS and Robotic Software Makespace, Cambridge UK 22nd February 2016

Approaching Automation Necessary for introducing a task Prioritize automation steps based

Learning Deep Broadband Network@HOME Hongjoo LEE Who am I? Machine Learning Engineer

From Deep Learning to Deep University: Cognitive Development of Intelligent Systems Mariia

Sony's deep learning software "Neural Network Libraries/Console and its use cases in Sony

CSE 2221 Software I: Software Components and CSE 2231 Software II: Software Development and

Hao Su July 6, 2017 Outline Overview of 3D deep learning 3D deep learning algorithms

Baseline A Library for Rapid Modeling, Experimentation and Development of Deep Learning

ACCELERATE DEEP LEARNING WITH NVIDIA'S DEEP LEARNING PLATFORM | STEPHEN JONES | GTC16 DEEP

Automating WordPress Development Chris Wiegman https://chriswiegman.com | @ChrisWiegman

Deep Learning on GPUs March 2016 What is Deep Learning? GPUs and DL AGENDA DL in practice

Reproducibility and Replicability in Deep Reinforcement Learning (and Other Deep Learning

Benchmarks and Middleware for Designing Convergent HPC, Big Data and Deep Learning Software Stacks

Deep Learning Next Meetups - Tom History, Approaches, Applications An Introduction by: Thomas

Image Classification with DIGITS NVIDIA Deep Learning Institute 1 DEEP LEARNING INSTITUTE DLI

Deep Neural Networks and Deep Reinforcement Learning Deep Learning, Goodfellow, Bengio and

Natural Language Processing with Deep Learning CS224N The Future of Deep Learning + NLP Kevin

A Single Platform Approach: Automating Receivables, Payables, & P Card Reconciliation

An Overview of Deep Residual Learning Semih Yagcioglu 01.03.2016 Deep Residual Learning

Automating Software Development with Deep Learning Emil Wallner, - PowerPoint PPT Presentation

Automating Software Development with Deep Learning Emil Wallner, 42, QCon So Paulo, 2019-05-7 01001001001010101010100111110110101010101000001010111010101010111101010111

1 Automating Machine Learning and Deep Learning Workflows 2 Information Name: Mourad

Automating Operations with Machine Learning Matt Callanan Senior Software Development Engineer

Automating High-Content Screening Image Analysis with Deep Learning GPU Technology Conference

Automating Cloud Deployment for Deep Learning Inference of Real-time Online Services Yang Li

N. Lane et al. l. DeepX: A Software Accelerator for Low Power Deep Learning In Inference on

Deep Learning Robot Demo - ROS and Robotic Software Makespace, Cambridge UK 22nd February 2016

Approaching Automation Necessary for introducing a task Prioritize automation steps based

Learning Deep Broadband Network@HOME Hongjoo LEE Who am I? Machine Learning Engineer

From Deep Learning to Deep University: Cognitive Development of Intelligent Systems Mariia

Sony's deep learning software &quot;Neural Network Libraries/Console and its use cases in Sony

CSE 2221 Software I: Software Components and CSE 2231 Software II: Software Development and

Hao Su July 6, 2017 Outline Overview of 3D deep learning 3D deep learning algorithms

Baseline A Library for Rapid Modeling, Experimentation and Development of Deep Learning

ACCELERATE DEEP LEARNING WITH NVIDIA'S DEEP LEARNING PLATFORM | STEPHEN JONES | GTC16 DEEP

Automating WordPress Development Chris Wiegman https://chriswiegman.com | @ChrisWiegman

Deep Learning on GPUs March 2016 What is Deep Learning? GPUs and DL AGENDA DL in practice

Reproducibility and Replicability in Deep Reinforcement Learning (and Other Deep Learning

Benchmarks and Middleware for Designing Convergent HPC, Big Data and Deep Learning Software Stacks

Deep Learning Next Meetups - Tom History, Approaches, Applications An Introduction by: Thomas

Image Classification with DIGITS NVIDIA Deep Learning Institute 1 DEEP LEARNING INSTITUTE DLI

Deep Neural Networks and Deep Reinforcement Learning Deep Learning, Goodfellow, Bengio and

Natural Language Processing with Deep Learning CS224N The Future of Deep Learning + NLP Kevin

A Single Platform Approach: Automating Receivables, Payables, &amp; P Card Reconciliation

An Overview of Deep Residual Learning Semih Yagcioglu 01.03.2016 Deep Residual Learning

Sony's deep learning software "Neural Network Libraries/Console and its use cases in Sony

A Single Platform Approach: Automating Receivables, Payables, & P Card Reconciliation