TensorFlow Serving, Deep Learning on Mobile, and Deeplearning4j on the JVM - Enterprise Deep Learning.pdf

Jun 9, 20174 likes1,447 views

1) The document discusses TensorFlow Serving, Deep Learning on Mobile, and Deeplearning4j on the JVM as presented by Sam Putnam on 6/8/2017. 2) It provides information on exporting models for TensorFlow Serving, deploying TensorFlow to Android, tools for mobile deep learning like Inception and MobileNets, and using Deeplearning4j on the JVM with integration with Spark. 3) The document shares links to resources on these topics and thanks sponsors while inviting people to join future discussions.

TensorFlow Serving, Deep
Learning on Mobile, and
Deeplearning4j on the JVM
Sam Putnam
6/8/2017
Want to learn live in New York?
I am teaching the Deploying Deep
Learning Track at Deep Learning Conf®
Tickets are available now:
www.DeepLearningConf.com

TensorFlow Serving
TensorFlow Serving, Deep Learning on Mobile, and Deeplearning4j on the JVM Sam Putnam
6/8/2017
TensorFlow Serving

Deep Learning on Mobile
TensorFlow Serving, Deep Learning on Mobile, and Deeplearning4j on the JVM Sam Putnam
6/8/2017
Deep Learning on Mobile

Deeplearning4j on the JVM
TensorFlow Serving, Deep Learning on Mobile, and Deeplearning4j on the JVM Sam Putnam
6/8/2017
Deeplearning4j on the JVM

Part 1 of 3
TensorFlow Serving
TensorFlow Serving
TensorFlow Serving, Deep Learning on Mobile, and Deeplearning4j on the JVM Sam Putnam
6/8/2017

TensorFlow Serving
TensorFlow Serving, Deep Learning on Mobile, and Deeplearning4j on the JVM Sam Putnam
Exporting Your Model
http://www.nqbao.com/blog/2017/02/tensorﬂow-exporting-model-for-serving/
6/8/2017

TensorFlow Serving
TensorFlow Serving, Deep Learning on Mobile, and Deeplearning4j on the JVM Sam Putnam
Question Answering at Zendesk
https://medium.com/zendesk-engineering/how-zendesk-serves-tensorﬂow-models-in-production-751ee22f0f4b
6/8/2017

TensorFlow Serving
TensorFlow Serving, Deep Learning on Mobile, and Deeplearning4j on the JVM Sam Putnam
Training to Production
https://medium.com/zendesk-engineering/how-zendesk-serves-tensorﬂow-models-in-production-751ee22f0f4b
6/8/2017

TensorFlow Serving
TensorFlow Serving, Deep Learning on Mobile, and Deeplearning4j on the JVM Sam Putnam
Inception V1 (GoogLeNet) ‘14
https://medium.com/zendesk-engineering/how-zendesk-serves-tensorﬂow-models-in-production-751ee22f0f4b
6/8/2017
https://www.quora.com/What-is-the-vanishing-gradient-problem
think
Oxford’s VGG 16
https://arxiv.org/pdf/1409.4842.pdf

TensorFlow Serving
TensorFlow Serving, Deep Learning on Mobile, and Deeplearning4j on the JVM Sam Putnam
https://research.googleblog.com/2016/08/improving-inception-and-image.html
6/8/2017
Inception V3 ’15 (2x deep, ~2x memory)
Softmax
https://www.youtube.com/watch?v=gNhogKJ_q7U

Part 2 of 3
Deep Learning on Mobile
Deep Learning on Mobile
TensorFlow Serving, Deep Learning on Mobile, and Deeplearning4j on the JVM Sam Putnam
6/8/2017

TensorFlow Serving, Deep Learning on Mobile, and Deeplearning4j on the JVM Sam Putnam
Deploying TensorFlow to Android (presumably works - I
don’t know because I have an iOS device)
Deep Learning on Mobile
https://chatbotslife.com/deploying-a-tensorﬂow-model-to-android-69d04d1b0cba
6/8/2017

Deep Learning on Mobile
TensorFlow Serving, Deep Learning on Mobile, and Deeplearning4j on the JVM Sam Putnam
Inception
https://github.com/hollance/Forge
6/8/2017
http://machinethink.net/blog/forge-neural-network-toolkit-for-metal/
https://youtu.be/XxDbKlIomhc

Deep Learning on Mobile
TensorFlow Serving, Deep Learning on Mobile, and Deeplearning4j on the JVM Sam Putnam
https://github.com/hollance/Forge
6/8/2017
http://machinethink.net/blog/forge-neural-network-toolkit-for-metal/
YOLO
https://youtu.be/OUdN4srAtRA

Deep Learning on Mobile
TensorFlow Serving, Deep Learning on Mobile, and Deeplearning4j on the JVM Sam Putnam
.dat or .bin files
https://github.com/LunarFlash/convolutional-neural-network-image-recognition
https://www.youtube.com/watch?v=EYP7099z6kk
6/8/2017

Deep Learning on Mobile
TensorFlow Serving, Deep Learning on Mobile, and Deeplearning4j on the JVM Sam Putnam
Speech Recognition and API call
https://github.com/marcdown/SayWhat https://www.youtube.com/watch?v=uM4Gav8Tk8A&feature=youtu.be
6/8/2017

Deep Learning on Mobile
TensorFlow Serving, Deep Learning on Mobile, and Deeplearning4j on the JVM Sam Putnam
Live Video Captioning
https://github.com/zats/SpeechRecognition https://www.youtube.com/watch?v=Xt8o3dlH7uQ
6/8/2017

Part 3 of 3
Deeplearning4j on the JVM
TensorFlow Serving, Deep Learning on Mobile, and Deeplearning4j on the JVM Sam Putnam
6/8/2017

TensorFlow Serving, Deep Learning on Mobile, and Deeplearning4j on the JVM Sam Putnam
Deeplearning4j is a Deep Learning
Framework that runs on the JVM
https://deeplearning4j.org/
6/8/2017

TensorFlow Serving, Deep Learning on Mobile, and Deeplearning4j on the JVM Sam Putnam
Today in the DL4j Gitter
https://gitter.im/deeplearning4j/deeplearning4j
6/8/2017

Deeplearning4j on the JVM
TensorFlow Serving, Deep Learning on Mobile, and Deeplearning4j on the JVM Sam Putnam
DL4j Integrates with Spark for Distributed Deep Learning
https://www.slideshare.net/jpatanooga/deep-learning-with-dl4j-hadoop-summit-2015/17
6/8/2017

Deeplearning4j on the JVM
TensorFlow Serving, Deep Learning on Mobile, and Deeplearning4j on the JVM Sam Putnam
From S3 to DL4j to Spark
https://dzone.com/articles/deep-learning-on-the-jvm
6/8/2017

Deeplearning4j on the JVM
TensorFlow Serving, Deep Learning on Mobile, and Deeplearning4j on the JVM Sam Putnam
Python Java for Training, Java for Deploy
https://youtu.be/R3lzuXPbybY?t=5m41s
6/8/2017

Thank you
TensorFlow Serving, Deep Learning on Mobile, and Deeplearning4j on the JVM Sam Putnam
Sam@EDeepLearning.com
Thank you to Google, Yoni Tsafir, Skymind, Bat Nguyen, ZenDesk, Others
who have published diagrams and photos. Slides are for today only.
Always looking for new members & new locations in Cambridge, US or
NYC & new speakers to present on Deep Learning in Production topics
https://www.slideshare.net/anirudhkoul/squeezing-deep-learning-into-mobile-phones/77
6/8/2017

While more and more people today have a fast Internet connection, there are plenty of other people that do not, e.g., in places where no ADSL or WAN is available. The aim of this talk is to present an Open Source project that combines multiple Internet access points (such as Wifi or mobile devices) into one single fast Internet connection, that it is easy to use, and fast to configure. This talk will present the starting requirements, the architecture of the first version (implemented based on creating a chain of proxy servers), the performed experiments to evaluate it, and current considerations on building the next version. Finally, this talk is also a call for help, maybe other South Tyroleans want to contribute to build a tool that allows people working or living in remote places to have a fast Internet connection through the combination of various weak ones.

GDG Morgantown, WV: Write code you can depend on!Logan Spears

When Will Drupal Die?chrisshattuck

The document discusses testing various real-time applications like Meteor, Pinpoint, and Mousepose. It then compares real-time frameworks like Meteor to traditional CMS platforms like Drupal, discussing Drupal's longevity but also how newer frameworks allow for faster development through features like being fully JavaScript-based and using a single language. The document suggests Drupal needs to adopt object-oriented patterns and modern practices to remain competitive as real-time applications that allow for more live and collaborative development become more popular.

Titanium @ MinnebarKevin Whinnery

The document is a presentation about building native mobile apps using JavaScript with Titanium Mobile. It introduces Titanium Mobile as a tool that allows building cross-platform native apps using web technologies like JavaScript. The presentation demonstrates building a "Hello World" app in Titanium Mobile and walks through code from the Snapost sample app. It concludes by providing resources for getting started with Titanium Mobile development.

Lessons Learned From Applications That Kicked Titanium's AssKevin Whinnery

This document discusses lessons learned from apps that performed better than Titanium apps in terms of cross-platform concerns, memory management, slow initialization times, multiple contexts, and code structure. It provides solutions for each problem area, such as not aiming for 100% code reuse across platforms, planning for platform differences, closing windows and nulling references to help Titanium cleanup memory, deferring script loading, avoiding multiple contexts, and building a suite of custom components for code structure. The document concludes with a demo and code walkthrough.

Transpiler’s are here to stayRyan Blunden

A Introduction to the World of Node, Javascript & SeleniumJames Eisenhauer

A Introduction to the World of Node, Javascript & Selenium by James Eisenhauer We will discuss the following: - What it takes to run Node.js - Node.js vs IO.js vs Node Foundation - NPM (Node Package Manager) - NVM (Node Version Manager) - Node Testing Tools like Jasmine & Mocha - Node Build Tools like Grunt & Gulp - Selenium Node.js many language bindings - WD.js, Webdriver.io, Webdriver.js, Nightwatch.js - Other Selenium Node Frameworks - Protractor.js, TheIntern.js - Testing Asynchronously Sponsored by O'Reilly

Better Swift from the Foundation up #tryswiftnyc17 09-06Carl Brown

Write Better JavaScriptKevin Whinnery

This document provides an overview of writing better JavaScript by Kevin Whinnery. It discusses both good and bad parts of JavaScript, including object-oriented programming techniques like prototypal inheritance. It also offers useful patterns like self-calling functions and the module pattern. The document recommends style guidelines and provides examples of techniques like call and apply. Finally, it discusses using JavaScript in Titanium Mobile apps and lists further reading resources.

12 tricks to avoid hackers breaks your CI / CDDaniel Garcia (a.k.a cr0hn)

This document discusses 12 tricks hackers use to compromise continuous integration and continuous delivery (CI/CD) systems. It outlines attacks such as installing malware via libraries, leaking secrets, executing malicious code in pipelines, consuming cloud services to cause outages, zip bombs, memory bombs, fork bombs, and compromising APIs. The document emphasizes the importance of limiting permissions, monitoring systems, and assuming insider attackers when hardening CI/CD pipelines and infrastructure.

Cross Platform Mobile Development in C#James Montemagno

Desenvolvimento moderno de aplicativos androidDiego Figueredo

This document discusses modern Android app development topics including architecture patterns like MVP, MVVM, and Clean Architecture. It also covers Kotlin and reactive programming with RxJava. Key topics covered include the benefits of Kotlin for Android development, using RxJava observables and observers to implement reactive patterns, and how architectural patterns like MVP can help by separating app concerns and making code more modular, testable, and maintainable.

Rooted con 2020 - from the heaven to hell in the CI - CDDaniel Garcia (a.k.a cr0hn)

This document discusses security concerns related to continuous integration and continuous delivery (CI/CD) pipelines. It begins by defining key CI/CD concepts like continuous integration, continuous delivery, pipelines, DevOps, and DevSecOps. It then details several security risks that can occur at different stages of the CI/CD process, including in source code, during building, in deployment, and within infrastructure. Specific attacks mentioned include sensitive information leaks, trojanized artifacts, zip bombs, memory bombs, and more. The document emphasizes the importance of monitoring, limiting permissions, and network isolation to help secure CI/CD systems.

Continuous Integration @ MeetMagento Germany 2015Aleksey Razbakov

Provisioning environments. A simplistic approachEder Roger Souza

This document discusses provisioning development environments using DevOps tools like Vagrant and Puppet. It introduces Vagrant as a way to create reproducible and portable virtual environments. Puppet is then presented as an automation tool to configure and manage the resources and applications within those environments. The document provides a high-level example of using these tools together to provision a load-balanced web application backed by MongoDB. It aims to demonstrate how DevOps practices like automation and cooperation between development and operations can help address challenges like frequent deployment and onboarding new team members.

Sonatype DevSecOps Leadership forum 2020Daniel Garcia (a.k.a cr0hn)

This document discusses how hackers can break CI/CD infrastructure by exploiting vulnerabilities at different stages of the software development process. It outlines attacks such as inserting malware in source code or libraries, exploiting privileged access in build pipelines to achieve remote code execution, deploying zip bombs or memory bombs to crash systems, and compromising shared infrastructure between development and production environments. The document emphasizes the importance of limiting permissions, isolating networks, monitoring for anomalies, and hardening CI/CD systems with the same care as production servers.

Prototype 151 Apiguestc360a2

This document is the second edition of "Prototype 1.5.1: The Complete API Reference" published in May 2007. It provides documentation for the Prototype JavaScript framework, which was created by Sam Stephenson in 2005 to ease development of dynamic web applications. The PDF version was created by Josh Clark but the content comes from the Prototype site and its intellectual property of Sam Stephenson and the Prototype core team.

Machine Intelligence at Google Scale: TensorFlowDataWorks Summit/Hadoop Summit

- TensorFlow is Google's open source machine learning library for developing and training neural networks and deep learning models. It operates using data flow graphs to represent computation. - TensorFlow can be used across many platforms including data centers, CPUs, GPUs, mobile phones, and IoT devices. It is widely used at Google across many products and research areas involving machine learning. - The TensorFlow library is used along with higher level tools in Google's machine learning platform including TensorFlow Cloud, Machine Learning APIs, and Cloud Machine Learning Platform to make machine learning more accessible and scalable.

Neural Networks with Google TensorFlowDarshan Patel

On-device machine learning: TensorFlow on AndroidYufeng Guo

This document discusses building machine learning models for mobile apps using TensorFlow. It describes the process of gathering training data, training a model using Cloud ML Engine, optimizing the model for mobile, and integrating it into an Android app. Key steps involve converting video training data to images, retraining an InceptionV3 model, optimizing the model size with graph transformations, and loading the model into an Android app. TensorFlow allows developing machine learning models that can run efficiently on mobile devices.

Introducing TensorFlow: The game changer in building "intelligent" applicationsRokesh Jankie

Deep Learning for Data Scientists - Data Science ATL Meetup Presentation, 201...Andrew Gardner

Note: these are the slides from a presentation at Lexis Nexis in Alpharetta, GA, on 2014-01-08 as part of the DataScienceATL Meetup. A video of this talk from Dec 2013 is available on vimeo at http://bit.ly/1aJ6xlt Note: Slideshare mis-converted the images in slides 16-17. Expect a fix in the next couple of days. --- Deep learning is a hot area of machine learning named one of the "Breakthrough Technologies of 2013" by MIT Technology Review. The basic ideas extend neural network research from past decades and incorporate new discoveries in statistical machine learning and neuroscience. The results are new learning architectures and algorithms that promise disruptive advances in automatic feature engineering, pattern discovery, data modeling and artificial intelligence. Empirical results from real world applications and benchmarking routinely demonstrate state-of-the-art performance across diverse problems including: speech recognition, object detection, image understanding and machine translation. The technology is employed commercially today, notably in many popular Google products such as Street View, Google+ Image Search and Android Voice Recognition. In this talk, we will present an overview of deep learning for data scientists: what it is, how it works, what it can do, and why it is important. We will review several real world applications and discuss some of the key hurdles to mainstream adoption. We will conclude by discussing our experiences implementing and running deep learning experiments on our own hardware data science appliance.

Large Scale Deep Learning with TensorFlow Jen Aman

Large-scale deep learning with TensorFlow allows storing and performing computation on large datasets to develop computer systems that can understand data. Deep learning models like neural networks are loosely based on what is known about the brain and become more powerful with more data, larger models, and more computation. At Google, deep learning is being applied across many products and areas, from speech recognition to image understanding to machine translation. TensorFlow provides an open-source software library for machine learning that has been widely adopted both internally at Google and externally.

Google TensorFlow Tutorial台灣資料科學年會

Deep Learning and Recurrent Neural Networks in the EnterpriseJosh Patterson

This document discusses deep learning and recurrent neural networks. It provides an overview of deep learning, including definitions, automated feature learning, and popular deep learning architectures. It also describes DL4J, a tool for building deep learning models in Java and Scala, and discusses applications of recurrent neural networks for tasks like anomaly detection using time series data and audio processing.

DeepLearning4J and Spark: Successes and Challenges - François Garillotsparktc

Deeplearning4J is an open-source, distributed deep learning library written for Java and Scala. It provides tools for training neural networks on distributed systems. While large companies can distribute training across many servers, Deeplearning4J allows other organizations to do distributed training as well. It includes libraries for vectorization, linear algebra, data preprocessing, model definition and training. The library aims to make deep learning more accessible to enterprises by allowing them to train models on their own large datasets.

DeepLearning4J and Spark: Successes and Challenges - François GarillotSteve Moore

At the recent Spark & Machine Learning Meetup in Brussels, François Garillot of Skymind delivered this lightning talk to a sold-out crowd. Specifically, François offered a tour of the DeepLearning4J architecture intermingled with applications. He went over the main blocks of this deep learning solution for the JVM that includes GPU acceleration, a custom n-dimensional array library, a parallelized data-loading swiss army tool, deep learning and reinforcement learning libraries — all with an easy-access interface. Along the way, he pointed out the strategic points of parallelization of computation across machines and gave insight on where Spark helps — and where it doesn't.

DeepLearning4J and Spark: Successes and Challenges - François Garillotsparktc

At the recent sold-out Spark & Machine Learning Meetup in Brussels, François Garillot of Skymind delivered a lightning talk called DeepLearning4J and Spark: Successes and Challenges. Specifically, François offered a tour of the DeepLearning4J architecture intermingled with applications. He went over the main blocks of this deep learning solution for the JVM that includes GPU acceleration, a custom n-dimensional array library, a parallelized data-loading swiss army tool, deep learning and reinforcement learning libraries — all with an easy-access interface. Along the way, he pointed out the strategic points of parallelization of computation across machines and gave insight on where Spark helps — and where it doesn't.

More Related Content

What's hot (11)

A Introduction to the World of Node, Javascript & SeleniumJames Eisenhauer

Better Swift from the Foundation up #tryswiftnyc17 09-06Carl Brown

Write Better JavaScriptKevin Whinnery

12 tricks to avoid hackers breaks your CI / CDDaniel Garcia (a.k.a cr0hn)

Cross Platform Mobile Development in C#James Montemagno

Desenvolvimento moderno de aplicativos androidDiego Figueredo

Rooted con 2020 - from the heaven to hell in the CI - CDDaniel Garcia (a.k.a cr0hn)

Continuous Integration @ MeetMagento Germany 2015Aleksey Razbakov

Provisioning environments. A simplistic approachEder Roger Souza

Sonatype DevSecOps Leadership forum 2020Daniel Garcia (a.k.a cr0hn)

Prototype 151 Apiguestc360a2

A Introduction to the World of Node, Javascript & SeleniumJames Eisenhauer

Better Swift from the Foundation up #tryswiftnyc17 09-06Carl Brown

Write Better JavaScriptKevin Whinnery

12 tricks to avoid hackers breaks your CI / CDDaniel Garcia (a.k.a cr0hn)

Cross Platform Mobile Development in C#James Montemagno

Desenvolvimento moderno de aplicativos androidDiego Figueredo

Rooted con 2020 - from the heaven to hell in the CI - CDDaniel Garcia (a.k.a cr0hn)

Continuous Integration @ MeetMagento Germany 2015Aleksey Razbakov

Provisioning environments. A simplistic approachEder Roger Souza

Sonatype DevSecOps Leadership forum 2020Daniel Garcia (a.k.a cr0hn)

Prototype 151 Apiguestc360a2

Viewers also liked (7)

Machine Intelligence at Google Scale: TensorFlowDataWorks Summit/Hadoop Summit

Neural Networks with Google TensorFlowDarshan Patel

On-device machine learning: TensorFlow on AndroidYufeng Guo

Introducing TensorFlow: The game changer in building "intelligent" applicationsRokesh Jankie

Deep Learning for Data Scientists - Data Science ATL Meetup Presentation, 201...Andrew Gardner

Large Scale Deep Learning with TensorFlow Jen Aman

Google TensorFlow Tutorial台灣資料科學年會

Machine Intelligence at Google Scale: TensorFlowDataWorks Summit/Hadoop Summit

Neural Networks with Google TensorFlowDarshan Patel

On-device machine learning: TensorFlow on AndroidYufeng Guo

Introducing TensorFlow: The game changer in building "intelligent" applicationsRokesh Jankie

Deep Learning for Data Scientists - Data Science ATL Meetup Presentation, 201...Andrew Gardner

Large Scale Deep Learning with TensorFlow Jen Aman

Google TensorFlow Tutorial台灣資料科學年會

Similar to TensorFlow Serving, Deep Learning on Mobile, and Deeplearning4j on the JVM - Enterprise Deep Learning.pdf (20)

Deep Learning and Recurrent Neural Networks in the EnterpriseJosh Patterson

DeepLearning4J and Spark: Successes and Challenges - François Garillotsparktc

DeepLearning4J and Spark: Successes and Challenges - François GarillotSteve Moore

DeepLearning4J and Spark: Successes and Challenges - François Garillotsparktc

Deep learning on a mixed cluster with deeplearning4j and sparkFrançois Garillot

Deep learning models can be distributed across a cluster to speed up training time and handle large datasets. Deeplearning4j is an open-source deep learning library for Java that runs on Spark, allowing models to be trained in a distributed fashion across a Spark cluster. Training a model involves distributing stochastic gradient descent (SGD) across nodes, with the key challenge being efficient all-reduce communication between nodes. Engineering high performance distributed training, such as with parameter servers, is important to reduce bottlenecks.

open source nn frameworks on cellphonesKoan-Sin Tan

Future of ai on the jvmAdam Gibson

This document discusses the future of artificial intelligence on the Java Virtual Machine (JVM). It outlines how machine learning frameworks are currently monolithic and make assumptions about data. The document proposes a micro-services approach to machine learning that separates out concerns like data pipelines, scoring, model training, and evaluation. This would help reduce lock-in and allow greater flexibility. It also discusses how new hardware like GPUs are better suited for deep learning and the role frameworks like Spark and Akka could play in distributed, real-time machine learning applications on the JVM.

DL4J at Workday MeetupDavid Kale

David Kale and Ruben Fizsel from Skymind talk about deep learning for the JVM and enterprise using deeplearning4j (DL4J). Deep learning (nouveau neural nets) have sparked a renaissance in empirical machine learning with breakthroughs in computer vision, speech recognition, and natural language processing. However, many popular deep learning frameworks are targeted to researchers and poorly suited to enterprise settings that use Java-centric big data ecosystems. DL4J bridges the gap, bringing high performance numerical linear algebra libraries and state-of-the-art deep learning functionality to the JVM.

"Large-Scale Deep Learning for Building Intelligent Computer Systems," a Keyn...Edge AI and Vision Alliance

For the full video of this presentation, please visit: http://www.embedded-vision.com/platinum-members/embedded-vision-alliance/embedded-vision-training/videos/pages/may-2016-embedded-vision-summit-google-keynote For more information about embedded vision, please visit: http://www.embedded-vision.com Jeff Dean, Senior Fellow at Google, presents the "Large-Scale Deep Learning for Building Intelligent Computer Systems" keynote at the May 2016 Embedded Vision Summit. Over the past few years, Google has built two generations of large-scale computer systems for training neural networks, and then applied these systems to a wide variety of research problems that have traditionally been very difficult for computers. Google has released its second generation system, TensorFlow, as an open source project, and is now collaborating with a growing community on improving and extending its functionality. Using TensorFlow, Google's research group has made significant improvements in the state-of-the-art in many areas, and dozens of different groups at Google use it to train state-of-the-art models for speech recognition, image recognition, various visual detection tasks, language modeling, language translation, and many other tasks. In this talk, Jeff highlights some of ways that Google trains large models quickly on large datasets, and discusses different approaches for deploying machine learning models in environments ranging from large datacenters to mobile devices. He will then discuss ways in which Google has applied this work to a variety of problems in Google's products, usually in close collaboration with other teams. This talk describes joint work with many people at Google.

Deep Learning in a nutshellHopeBay Technologies, Inc.

Guglielmo iozzia - Google I/O extended dublin 2018Guglielmo Iozzia

This document discusses deep learning and options for implementing it on the Java Virtual Machine (JVM). It introduces DeepLearning4J (DL4J) as an open source deep learning library for the JVM. It also discusses TensorFlow and Keras, noting that while TensorFlow is mostly Python-based, Keras models can be imported into DL4J. An example is provided of using DataVec to transform data and DL4J to build and train a convolutional neural network model on Spark. The document encourages exploring existing neural network models online and moving deep learning implementations into production.

Deep Learning: DL4J and DataVecJosh Patterson

This document discusses using DL4J and DataVec to build deep learning workflows for modeling time series sensor data with recurrent neural networks. It provides an example of loading and transforming sensor data with DataVec, configuring an RNN with DL4J, and training the model both locally and distributed on Spark. The overall workflow involves extracting, transforming, and loading data with DataVec, vectorizing it, modeling with DL4J, evaluating performance, and deploying trained models for execution on Spark/Hadoop platforms.

Josh Patterson, Advisor, Skymind – Deep learning for Industry at MLconf ATL 2016MLconf

This document discusses using DL4J and DataVec to build deep learning workflows for modeling time series sensor data with recurrent neural networks. It provides an example of loading and transforming time series data from sensors using DataVec, configuring an RNN using DL4J to classify the trends in the sensor data, and training the network both locally and distributed on Spark. The document promotes DL4J and DataVec as tools that can help enterprises overcome challenges to operationalizing deep learning and producing machine learning models at scale.

Deep Learning for Artificial Intelligence (AI)Er. Shiva K. Shrestha

The document provides an overview of deep learning including: - Defining deep learning as a class of machine learning algorithms that use multiple levels of representation and nonlinear processing units. - Explaining that deep learning aims to learn representations of data without specifying features, in contrast to traditional machine learning which relies on human-engineered features. - Highlighting applications of deep learning like computer vision, speech recognition, machine translation and more which have achieved expert-level performance.

Sjug #26 ml is in java but is dl too - ver1.04 - tomasz sikora 2018-03-23Tomasz Sikora

Machine learning and deep learning techniques are present in Java through various libraries. Deep learning allows neural networks to learn from vast amounts of data through multilayer architectures like convolutional neural networks (CNNs) and recurrent neural networks (RNNs). The talk discussed several popular Java libraries that support both traditional machine learning algorithms and deep learning models, including DL4J, TensorFlow, Keras, and H2O. It provided examples of training deep learning models on MNIST and CIFAR10 datasets in DL4J and compared performance between DL4J and TensorFlow.

How to Build Deep Learning ModelsJosh Patterson

Deep learning and Apache SparkQuantUniversity

Interest is growing in the Apache Spark community in using Deep Learning techniques and in the Deep Learning community in scaling algorithms with Apache Spark. A few of them to note include: · Databrick’s efforts in scaling Deep learning with Spark · Intel announcing the BigDL: A Deep learning library for Spark · Yahoo’s recent efforts to opensource TensorFlowOnSpark In this lecture we will discuss the key use cases and developments that have emerged in the last year in using Deep Learning techniques with Spark.

Running deep neural nets in your Java application with Deeplearning4jAlexander Fedintsev

Georgia Tech cse6242 - Intro to Deep Learning and DL4JJosh Patterson

Enhance your java applications with deep learning using deep nettsZoran Sevarac, PhD

Deep Learning and Recurrent Neural Networks in the EnterpriseJosh Patterson

DeepLearning4J and Spark: Successes and Challenges - François Garillotsparktc

DeepLearning4J and Spark: Successes and Challenges - François GarillotSteve Moore

DeepLearning4J and Spark: Successes and Challenges - François Garillotsparktc

Deep learning on a mixed cluster with deeplearning4j and sparkFrançois Garillot

open source nn frameworks on cellphonesKoan-Sin Tan

Future of ai on the jvmAdam Gibson

DL4J at Workday MeetupDavid Kale

"Large-Scale Deep Learning for Building Intelligent Computer Systems," a Keyn...Edge AI and Vision Alliance

Deep Learning in a nutshellHopeBay Technologies, Inc.

Guglielmo iozzia - Google I/O extended dublin 2018Guglielmo Iozzia

Deep Learning: DL4J and DataVecJosh Patterson

Josh Patterson, Advisor, Skymind – Deep learning for Industry at MLconf ATL 2016MLconf

Deep Learning for Artificial Intelligence (AI)Er. Shiva K. Shrestha

Sjug #26 ml is in java but is dl too - ver1.04 - tomasz sikora 2018-03-23Tomasz Sikora

How to Build Deep Learning ModelsJosh Patterson

Deep learning and Apache SparkQuantUniversity

Running deep neural nets in your Java application with Deeplearning4jAlexander Fedintsev

Georgia Tech cse6242 - Intro to Deep Learning and DL4JJosh Patterson

Enhance your java applications with deep learning using deep nettsZoran Sevarac, PhD

More from Sam Putnam [Deep Learning] (6)

Executing Deep Learning Strategies Masterclass Preview - Enterprise Deep Lear...Sam Putnam [Deep Learning]

The document outlines an agenda for a one-day workshop on executing deep learning strategies. The day is divided into a morning and afternoon session. The morning includes introductions to machine learning, deep learning, and question and answer sessions. The afternoon covers developing awareness of deep learning technologies, customizing deep learning solutions for specific tasks, and applying deep learning across business teams. The document provides details on the timing and content of each session.

Deploying Enterprise Deep Learning Masterclass Preview - Enterprise Deep Lea...Sam Putnam [Deep Learning]

This document summarizes Sam Putnam's presentation on deploying enterprise deep learning. It discusses how deep learning was used to analyze housing price data and predict prices. A neural network model was built using TensorFlow that improved on previous linear regression and gradient boosted decision tree models. The presentation provides an overview of deep learning concepts like neural networks, activation functions, and model architectures for different data types. It emphasizes real-world considerations for developing and deploying deep learning models in a production setting.

Introduction to Machine Learning for Heathcare, Finance, Energy, and Commerce...Sam Putnam [Deep Learning]

Introduction to Machine Learning for Healthcare, Finance, Energy, and Commerc...Sam Putnam [Deep Learning]

Transforming Healthcare, Finance, Energy, and Commerce with Machine Learning,...Sam Putnam [Deep Learning]

Quality and Testing of AI Algorithms - Enterprise Deep LearningSam Putnam [Deep Learning]

Executing Deep Learning Strategies Masterclass Preview - Enterprise Deep Lear...Sam Putnam [Deep Learning]

Deploying Enterprise Deep Learning Masterclass Preview - Enterprise Deep Lea...Sam Putnam [Deep Learning]

Introduction to Machine Learning for Heathcare, Finance, Energy, and Commerce...Sam Putnam [Deep Learning]

Introduction to Machine Learning for Healthcare, Finance, Energy, and Commerc...Sam Putnam [Deep Learning]

Transforming Healthcare, Finance, Energy, and Commerce with Machine Learning,...Sam Putnam [Deep Learning]

Quality and Testing of AI Algorithms - Enterprise Deep LearningSam Putnam [Deep Learning]

Recently uploaded (20)

Scalefusion Remote Access for Apple DevicesScalefusion

🔌Tried restarting. 🔁Then updating. 🔎Then Googled a fix. And then it crashed. Guess who has to fix it? You. And who’ll help you? - Scalefusion. Scalefusion steps in with real-time access, not just remote hope. Support for Apple devices that support you (and them) to do more. For more: https://scalefusion.com/remote-access-software-mac https://scalefusion.com/es/remote-access-software-mac https://scalefusion.com/fr/remote-access-software-mac https://scalefusion.com/pt-br/remote-access-software-mac https://scalefusion.com/nl/remote-access-software-mac https://scalefusion.com/de/remote-access-software-mac https://scalefusion.com/ru/remote-access-software-mac

Top 5 Odoo Modules for the EPC Industry.pdfSatishKumar2651

The Engineering, Procurement, and Construction (EPC) industry is highly complex, involving multiple stakeholders, high-value procurement, strict timelines, and resource-heavy project execution. In such a demanding environment, using the right ERP system is not a luxury—it's a necessity. This presentation highlights the Top 5 Odoo ERP modules specifically tailored to meet the dynamic needs of the EPC sector. Whether you're managing large-scale infrastructure projects or specialized engineering contracts, Odoo provides an integrated solution that can streamline your entire project lifecycle. 🔍 What’s Inside: Key challenges faced by EPC companies Overview of essential Odoo modules Real-world benefits of using Project, Purchase, Inventory, Field Service, and Accounting modules How these modules contribute to cost control, real-time visibility, and operational efficiency This presentation is designed for EPC business owners, project managers, procurement heads, and field service teams who are exploring digital transformation through Odoo ERP.

Feeling Lost in the Blue? Exploring a New Path: AI Mental Health Counselling ...officeiqai

Marketing And Sales Software Services.pptxjulia smits

German Marketo User Group - May 2025 survey resultsBradBedford3

Autoposting.ai Sales Deck - Skyrocket your LinkedIn's ROIUdit Goenka

1billion people scroll, only 1 % post… That’s your opening to hijack LinkedIn—and Autoposting.ai is the unfair weapon Slideshare readers are hunting for… LinkedIn drives 80 % of social B2B leads, converts 2× better than every other network, yet 87 % of pros still choke on the content hamster-wheel… They burn 25 h a month writing beige posts, miss hot trends, then watch rivals scoop the deals… Enter Autoposting.ai, the first agentic-AI engine built only for LinkedIn domination… It spies on fresh feed data, cracks trending angles before they peak, and spins voice-perfect thought-leadership that sounds like you—not a robot… Slides in play: • 78 % average engagement lift in 90 days… • 3.2× qualified-lead surge over manual posting… • 42 % marketing time clawed back, week after week… Real users report 5-8× ROI inside the first quarter, some crossing $1 M ARR six months faster… Why does it hit harder than Taplio, Supergrow, generic AI writers? • Taplio locks key features behind $149+ tiers… Autoposting gives you everything at $29… • Supergrow churns at 20 % because “everyone” is no-one… Autoposting laser-targets • • LinkedIn’s gold-vein ICPs and keeps them glued… • ChatGPT needs prompts, edits, scheduling hacks… Autoposting researches, writes, schedules—and optimizes send-time in one sweep… Need social proof? G2 reviews scream “game-changer”… Agencies slash content production 80 % and triple client capacity… CXOs snag PR invites and investor DMs after a single week of daily posts… Employee advocates hit 8× reach versus company pages and pump 25 % more SQLs into the funnel… Feature bullets for the skim-reader: • Agentic Research Engine—tracks 27+ data points, finds gaps your rivals ignore… • Real Voice Match—your tone, slang, micro-jokes, intact… • One-click Multiplatform—echo winning posts to Twitter, Insta, Facebook… • Team Workspaces—spin up 10 seats without enterprise red tape… • AI Timing—drops content when your buyers actually scroll, boosting first-hour velocity by up to 4×… Risk? Zero… Free 7-day trial, 90-day results guarantee—hit 300 % ROI or walk away… but the clock is ticking while competitors scoop your feed… So here’s the ask: Swipe down, smash the “Download” or “Try Now” button, and let Autoposting.ai turn Slideshare insights into pipeline—before today’s trending topic vanishes… The window is open… How loud do you want your LinkedIn megaphone?

Key Characteristics of High-Performing Insurance Broker SoftwareInsurance Tech Services

Offensive Security Penetration Testing Purple Box

AI Alternative - Discover the best AI tools and their alternativesAI Alternative

AIAlternative.co is a comprehensive directory designed to help users discover, compare, and evaluate AI tools across various domains. Its primary goal is to assist individuals and businesses in finding the most suitable AI solutions tailored to their specific needs. Key Features - Curated AI Tool Listings: The platform offers detailed information on a wide range of AI tools, including their functionalities, use cases, and alternatives. This allows users to make informed decisions based on their requirements. - Alternative Suggestions: For each listed AI tool, aialternative.co provides suggestions for similar or alternative tools, facilitating easier comparison and selection. - Regular Updates: The directory is consistently updated to include the latest AI innovations, ensuring users have access to the most current tools available in the market. Browse All Tools here: https://aialternative.co/

Why-Choose-an-Authorised-Microsoft-Reseller.pptxMichael cole

Software Risk and Quality management.pptxHassanBangash9

Secure and Simplify IT Management with ManageEngine Endpoint Central.pdfNorthwind Technologies

Shortcomings of EHS Software – And How to Overcome ThemTECH EHS Solution

Shortcomings of EHS Software—and What Overcomes Them What you'll learn in just 8 slides: - 🔍 Why most EHS software implementations struggle initially - 🚧 3 common pitfalls: adoption, workflow disruption, and delayed ROI - 🛠️ Practical solutions that deliver long-term value - 🔐 Key features: centralization, security, affordability - 📈 Why the pros outweigh the cons Perfect for HSE heads, plant managers, and compliance leads! #EHS #TECHEHS #WorkplaceSafety #EHSCompliance #EHSManagement #ehssoftware #safetysoftware

Facility Management Solution - TeroTAM CMMS SoftwareTeroTAM

Upscale your Operational Excellence with systematic & streamlined. Key Features of TeroTAM ➢ Asset Management ➢ Preventive Maintenance ➢ Complaint Management Solution ➢ Task & Escalation Management ➢ Location Management ➢ Stroe Condition Assessment ➢ Facility Condition Assessment ➢ Workflow Management ➢ Vendor & Service Management ➢ Staff Management and Tracking ➢ Analytics/Reports

Delivering More with Less: AI Driven Resource Management with OnePlan OnePlan Solutions

Delivering more with less is an age-old problem. Smaller budgets, leaner teams, and greater uncertainty make the path to success unclear. Combat these issues with confidence by leveraging the best practices that help PMOs balance workloads, predict bottlenecks, and ensure resources are deployed effectively, using OnePlan’s AI forecasting capabilities, especially when organizations must deliver more with fewer people.

Software Quality Assurance (Models).pptxHibbaTabeer

BoxLang-Dynamic-AWS-Lambda by Luis Majano.pdfOrtus Solutions, Corp

🤖🤖🤖Charasteristic of Agentic AI 🤖🤖🤖MOSIUOA WESI

This presentation provides an overview of Agentic AI, intelligent systems capable of autonomous decision-making and action with minimal supervision. It highlights how these systems interact with their environment, learn over time, and adapt to complex situations. The content outlines the transformative potential of Agentic AI across industries and emphasizes the importance of understanding its core features and challenges.

What's-New-with-BoxLang-Brad Wood.pptx.pdfOrtus Solutions, Corp

Improving Engagement with CRM Software for Instance AgentsInsurance Tech Services

Scalefusion Remote Access for Apple DevicesScalefusion

Top 5 Odoo Modules for the EPC Industry.pdfSatishKumar2651

Feeling Lost in the Blue? Exploring a New Path: AI Mental Health Counselling ...officeiqai

Marketing And Sales Software Services.pptxjulia smits

German Marketo User Group - May 2025 survey resultsBradBedford3

Autoposting.ai Sales Deck - Skyrocket your LinkedIn's ROIUdit Goenka

Key Characteristics of High-Performing Insurance Broker SoftwareInsurance Tech Services

Offensive Security Penetration Testing Purple Box

AI Alternative - Discover the best AI tools and their alternativesAI Alternative

Why-Choose-an-Authorised-Microsoft-Reseller.pptxMichael cole

Software Risk and Quality management.pptxHassanBangash9

Secure and Simplify IT Management with ManageEngine Endpoint Central.pdfNorthwind Technologies

Shortcomings of EHS Software – And How to Overcome ThemTECH EHS Solution

Facility Management Solution - TeroTAM CMMS SoftwareTeroTAM

Delivering More with Less: AI Driven Resource Management with OnePlan OnePlan Solutions

Software Quality Assurance (Models).pptxHibbaTabeer

BoxLang-Dynamic-AWS-Lambda by Luis Majano.pdfOrtus Solutions, Corp

🤖🤖🤖Charasteristic of Agentic AI 🤖🤖🤖MOSIUOA WESI

What's-New-with-BoxLang-Brad Wood.pptx.pdfOrtus Solutions, Corp

Improving Engagement with CRM Software for Instance AgentsInsurance Tech Services

TensorFlow Serving, Deep Learning on Mobile, and Deeplearning4j on the JVM - Enterprise Deep Learning.pdf

1. TensorFlow Serving, Deep Learning on Mobile, and Deeplearning4j on the JVM Sam Putnam 6/8/2017 Want to learn live in New York? I am teaching the Deploying Deep Learning Track at Deep Learning Conf® Tickets are available now: www.DeepLearningConf.com

2. TensorFlow Serving TensorFlow Serving, Deep Learning on Mobile, and Deeplearning4j on the JVM Sam Putnam 6/8/2017 TensorFlow Serving

3. Deep Learning on Mobile TensorFlow Serving, Deep Learning on Mobile, and Deeplearning4j on the JVM Sam Putnam 6/8/2017 Deep Learning on Mobile

4. Deeplearning4j on the JVM TensorFlow Serving, Deep Learning on Mobile, and Deeplearning4j on the JVM Sam Putnam 6/8/2017 Deeplearning4j on the JVM

5. Part 1 of 3 TensorFlow Serving TensorFlow Serving TensorFlow Serving, Deep Learning on Mobile, and Deeplearning4j on the JVM Sam Putnam 6/8/2017

6. TensorFlow Serving TensorFlow Serving, Deep Learning on Mobile, and Deeplearning4j on the JVM Sam Putnam Exporting Your Model http://www.nqbao.com/blog/2017/02/tensorﬂow-exporting-model-for-serving/ 6/8/2017

7. TensorFlow Serving TensorFlow Serving, Deep Learning on Mobile, and Deeplearning4j on the JVM Sam Putnam Question Answering at Zendesk https://medium.com/zendesk-engineering/how-zendesk-serves-tensorﬂow-models-in-production-751ee22f0f4b 6/8/2017

8. TensorFlow Serving TensorFlow Serving, Deep Learning on Mobile, and Deeplearning4j on the JVM Sam Putnam Training to Production https://medium.com/zendesk-engineering/how-zendesk-serves-tensorﬂow-models-in-production-751ee22f0f4b 6/8/2017

9. TensorFlow Serving TensorFlow Serving, Deep Learning on Mobile, and Deeplearning4j on the JVM Sam Putnam Inception V1 (GoogLeNet) ‘14 https://medium.com/zendesk-engineering/how-zendesk-serves-tensorﬂow-models-in-production-751ee22f0f4b 6/8/2017 https://www.quora.com/What-is-the-vanishing-gradient-problem think Oxford’s VGG 16 https://arxiv.org/pdf/1409.4842.pdf

10. TensorFlow Serving TensorFlow Serving, Deep Learning on Mobile, and Deeplearning4j on the JVM Sam Putnam https://research.googleblog.com/2016/08/improving-inception-and-image.html 6/8/2017 Inception V3 ’15 (2x deep, ~2x memory) Softmax https://www.youtube.com/watch?v=gNhogKJ_q7U

11. Part 2 of 3 Deep Learning on Mobile Deep Learning on Mobile TensorFlow Serving, Deep Learning on Mobile, and Deeplearning4j on the JVM Sam Putnam 6/8/2017

12. TensorFlow Serving, Deep Learning on Mobile, and Deeplearning4j on the JVM Sam Putnam Deploying TensorFlow to Android (presumably works - I don’t know because I have an iOS device) Deep Learning on Mobile https://chatbotslife.com/deploying-a-tensorﬂow-model-to-android-69d04d1b0cba 6/8/2017

13. Deep Learning on Mobile TensorFlow Serving, Deep Learning on Mobile, and Deeplearning4j on the JVM Sam Putnam Inception https://github.com/hollance/Forge 6/8/2017 http://machinethink.net/blog/forge-neural-network-toolkit-for-metal/ https://youtu.be/XxDbKlIomhc

14. Deep Learning on Mobile TensorFlow Serving, Deep Learning on Mobile, and Deeplearning4j on the JVM Sam Putnam https://github.com/hollance/Forge 6/8/2017 http://machinethink.net/blog/forge-neural-network-toolkit-for-metal/ YOLO https://youtu.be/OUdN4srAtRA

15. Deep Learning on Mobile TensorFlow Serving, Deep Learning on Mobile, and Deeplearning4j on the JVM Sam Putnam https://github.com/hollance/Forge 6/8/2017 http://machinethink.net/blog/forge-neural-network-toolkit-for-metal/ MobileNets https://youtu.be/0vBsU__JTlA

16. Deep Learning on Mobile TensorFlow Serving, Deep Learning on Mobile, and Deeplearning4j on the JVM Sam Putnam https://github.com/hollance/Forge 6/8/2017 http://machinethink.net/blog/forge-neural-network-toolkit-for-metal/ MNIST (of course) https://youtu.be/EL78-Rgoyfw

17. Deep Learning on Mobile TensorFlow Serving, Deep Learning on Mobile, and Deeplearning4j on the JVM Sam Putnam .dat or .bin files https://github.com/LunarFlash/convolutional-neural-network-image-recognition https://www.youtube.com/watch?v=EYP7099z6kk 6/8/2017

18. Deep Learning on Mobile TensorFlow Serving, Deep Learning on Mobile, and Deeplearning4j on the JVM Sam Putnam Speech Recognition and API call https://github.com/marcdown/SayWhat https://www.youtube.com/watch?v=uM4Gav8Tk8A&feature=youtu.be 6/8/2017

19. Deep Learning on Mobile TensorFlow Serving, Deep Learning on Mobile, and Deeplearning4j on the JVM Sam Putnam Live Video Captioning https://github.com/zats/SpeechRecognition https://www.youtube.com/watch?v=Xt8o3dlH7uQ 6/8/2017

20. Part 3 of 3 Deeplearning4j on the JVM TensorFlow Serving, Deep Learning on Mobile, and Deeplearning4j on the JVM Sam Putnam 6/8/2017

21. TensorFlow Serving, Deep Learning on Mobile, and Deeplearning4j on the JVM Sam Putnam Deeplearning4j is a Deep Learning Framework that runs on the JVM https://deeplearning4j.org/ 6/8/2017

22. TensorFlow Serving, Deep Learning on Mobile, and Deeplearning4j on the JVM Sam Putnam Today in the DL4j Gitter https://gitter.im/deeplearning4j/deeplearning4j 6/8/2017

23. Deeplearning4j on the JVM TensorFlow Serving, Deep Learning on Mobile, and Deeplearning4j on the JVM Sam Putnam DL4j Integrates with Spark for Distributed Deep Learning https://www.slideshare.net/jpatanooga/deep-learning-with-dl4j-hadoop-summit-2015/17 6/8/2017

24. Deeplearning4j on the JVM TensorFlow Serving, Deep Learning on Mobile, and Deeplearning4j on the JVM Sam Putnam From S3 to DL4j to Spark https://dzone.com/articles/deep-learning-on-the-jvm 6/8/2017

25. Deeplearning4j on the JVM TensorFlow Serving, Deep Learning on Mobile, and Deeplearning4j on the JVM Sam Putnam Python Java for Training, Java for Deploy https://youtu.be/R3lzuXPbybY?t=5m41s 6/8/2017

26. Thank you TensorFlow Serving, Deep Learning on Mobile, and Deeplearning4j on the JVM Sam Putnam [email protected] Thank you to Google, Yoni Tsafir, Skymind, Bat Nguyen, ZenDesk, Others who have published diagrams and photos. Slides are for today only. Always looking for new members & new locations in Cambridge, US or NYC & new speakers to present on Deep Learning in Production topics https://www.slideshare.net/anirudhkoul/squeezing-deep-learning-into-mobile-phones/77 6/8/2017

TensorFlow Serving, Deep Learning on Mobile, and Deeplearning4j on the JVM - Enterprise Deep Learning.pdf

Recommended

More Related Content

What's hot (11)

Viewers also liked (7)

Similar to TensorFlow Serving, Deep Learning on Mobile, and Deeplearning4j on the JVM - Enterprise Deep Learning.pdf (20)

More from Sam Putnam [Deep Learning] (6)

Recently uploaded (20)

TensorFlow Serving, Deep Learning on Mobile, and Deeplearning4j on the JVM - Enterprise Deep Learning.pdf