Deep learning in Java, from the team that builds it.
Tutorials, releases, use cases and conference talks from the Deep Netts team.
More posts51
JavaOne 2026 Keynote (Video)
At Java One 2026 Keynote, the startup panel brought together founders leveraging Java to build their businesses.
JavaOne 2026: Building Java Native AI for Enterprise Applications
At Java One 2026, in Building Java Native AI for Enterprise Applications, I’ll show how teams can build and run AI directly in Java, whether you’re moving from prototype to production or bringing an existing model into a Java environment.
GPU 400x faster than CPU with Deep Netts using Project Panama
At Devoxx Belgium 2025, we presented the results of a new benchmark that demonstrates just how far Java has come for AI workloads – especially with the latest improvements in Java 25’s Foreign Function & Memory (FFM) API and the Deep Netts AI platform running natively on GPUs.
Devoxx Belgium – Java as an AI development Platform
We are excited to announce my upcoming session at Devoxx Belgium 2025, where we’ll explore how AI truly belongs in Java.
Deep Netts and Project Panama: A Scalable, Secure, and High-Performance AI Solution in Java
Enterprises today are racing to integrate Artificial Intelligence into their core operations.
Project Panama: Powering AI/ML in the Java Ecosystem
Artificial Intelligence (AI) and Machine Learning (ML) are transforming industries, but they come with demanding performance requirements.
Why JSR 381 Matters: Bringing AI-Powered Vision to Java
Artificial Intelligence is transforming industries, and Java – one of the world’s most widely used programming languages – needs to evolve with it.
Java One 2025, Wednesday, March 19
Revolutionizing Science: How Java AI Accelerated Scientific Data Analysis 5000x. A prime example of this transformation is the use of the Java-based AI library Deep Netts, which has achieved an astonishing 5000x acceleration in scientific data analysis.
What's new in JAVA 23? JEP Explained. JEP 469: Vector API
Learn more about vector and scalar computations and the Vector API in the latest episode of JEP Explained.
Deep Netts 3.1.1.: New version of Java deep learning library and developer tools released
We are excited to announce the latest release of Deep Netts, bringing a series of significant upgrades and new features designed to enhance performance, simplify model development, and improve overall user experience.
Deep Netts Now Powered by GPU for Lightning-Fast AI Inference
With the release of Deep Netts 3.1.1, we are excited to introduce GPU support for inference, bringing a new level of performance to deep learning models.
Open Source Deep Learning in Java – Deep Netts Community Edition
What is Deep Netts Community Edition? A free open-source version of Deep Netts deep learning Java library.
JSR 381 – The standard Java API for Machine Learning
JSR 381, also known as the Java Specification Request 381, is a proposal within the Java Community Process (JCP) aimed at standardizing APIs for defining and executing deep learning models in Java.
Exploring Visual Classification with Deep Learning in Java Using Deep Netts
Visual classification, the process of categorizing images into distinct classes or categories, lies at the heart of various applications, from object recognition in autonomous vehicles to medical image analysis.
Deep Learning in Java for analyzing complex molecular structures
Curious about the groundbreaking research behind the SARS-CoV-2 spike protein dynamics? Look no further than latest scientific paper by Oscar Bastidas and our Zoran Sevarac, published in Nature Scientific Reports!
How to Do Image Recognition Using Deep Learning in Java
Learn how to make and implement image recognition in Java using deep learning techniques in this comprehensive tutorial.
Demystifying OpenJDK Turmoil (For Free)
The entire Java ecosystem has been going through a lot of turmoil with a shortened release cycle combined with continual and significant Java licensing changes.
Neural network visual Weights Analysis tool
Neural network visual Weights Analysis tool ready for the next Deep Netts release. It helps understanding what’s going on inside layers, and debugging trained networks.
Deep Learning in Java for Nuclear Physics using Deep Netts
The CLAS12 detector at Jefferson Lab conducts nuclear physics experiments to study the structure of nucleons and new particle states.
Open Source Deep Learning in Java – Deep Netts Community Edition
What is Deep Netts Community Edition? A free open-source version of Deep Netts Java deep learning library.
[Video] Veštačka inteligencija se približava ljudskoj?
Suosnivač Deep Netts-a i profesor FON-a na Katedri za softversko inženjerstvo Zoran Ševarac rekao je da veštačka inteligencija trenutno ne može nadmašiti ljudsku, ali da se u bliskoj budućnost može očekivati da joj se veoma približi.
Image Classification in Java Using Deep Learning
This tutorial shows you how to build simple image recognition aka binary image classifier in pure Java.
Deep Netts @ JavaOne 2022 in Las Vegas
Deep Netts will be presented at a premium Java conference JavaOne in Las Vegas as a part of the session Make your Java Apps Learn and See.
Tensorflow Support for Deep Netts 3 Has Been Released
Tensorflow support in Deep Netts enables import of Tensorflow models into Deep Netts and easily deploy them into Java applications.
What Is The Difference Between Artificial Intelligence, Machine Learning and Deep Learning?
Although these terms are used interchangeably, they are not the same. Essentially Deep Learning is a type of Machine Learning, and Machine Learning is a type of Artificial intelligence.
Using Deep Learning in Java for Image Recognition
This tutorial walks you through building state of the art AI based on deep learning for image recognition using Java. It will help you to get started with modern AI development using your Java skills.
[Video] Java-Friendly Machine Learning With the JSR381
Java-Friendly Machine Learning With the JSR381 is standard API for visual recognition using machine learning in Java.
Deep Netts 2.1.0 Has Been Released
Deep Netts 2.1.0 Has Been Released: Better user experience and debugging tools, Improved performance for all types of networks.
Deep Netts v2.0.1 Has Been Released
Deep Netts v2.0.1 has been released and is available for free download. This release brings a number of usability and security improvements.
Visual Recognition for Chess using Deep Learning in Java on Android
Over the last few decades, the technological advancement in the Artificial Intelligence (AI) field has greatly assisted many chess grand masters’ preparation as well as understanding chess theory.
Modern Machine Vision from Basics to Advanced Deep Learning
Zoran Sevarac, Associate Professor at the University of Belgrade and Co-founder and CEO of Deep Netts, presents the “Modern Machine Vision from Basics to Advanced Deep Learning” tutorial at the May 2021 Embedded Vision Summit.
Deep Netts v2.0 Has Been Released
Deep Netts 2.0.0 is out! With 2.0 release Deep Netts has reached an important milestone after testing through real world use cases and pilot projects.
Deep Learning in Drug Discovery – A New Frontier
Learn how Deep Netts advances scientific research in pharmaceutical industry and solves technical problems for deep learning in Java.
Deep Netts v1.3 Has Been Released
The new release of Deep Netts v1.3 brings advanced features and improvements: improved performance and accuracy, Visual Machine learning Workflow, Scatter-plot matrix and histogram.
JSR381 – Visual Recognition for Java – A Java-Friendly ML API at jChampions Conference
JSR 381 is a standard Java API for Machine learning, designed with the goal to simplify machine learning in Java for non-experts.
Cloud Classification using Deep Learning in Java
Cloud classification is the task of assigning cloud images to corresponding types/categories. This tutorial will guide you on how to create an advanced deep learning model for image classification, even if you’re not an expert in image analysis and deep learning.
Enhance your Java applications with Deep Learning using Deep Netts Session at Oracle Groundbreakers EMEA Tour
Learn how you can easily add machine learning capabilities to your Java application using Deep Netts.
Parking Lot Occupancy Detection using Deep Learning in Java
This video tutorial shows you how you can use Deep Netts to create visual parking lot occupancy detection using deep learning.
Deep Netts 1.2 Has Been Released
The new release of Deep Netts v1.2 brings several exciting new features and improvements: Higher Performance, Better accuracy, New optimization algorithms.
How a 14-year-old Learned Deep Learning in Java using Deep Netts
You don't need PhD or to be math wizard in order to use deep learning anymore.
JSR381 Visual Recognition for Java – Machine Learning for Java developers @ NYJUG
We all know Machine Learning (ML) is a huge, long-term global trend that affects every part of the stack from the user to the hardware.
From Basic Machine Learning to Deep Learning in 5 Minutes
Deep learning algorithms evolved from well known mathematical procedures, and the idea of this post is to give a brief overview of that evolution.
Deep Learning Tutorial for Java Developers
This series of tutorials will introduce you to deep learning as quick as possible, and give you enough understanding so you can start working on your own projects immediately.
Machine Learning Tutorial for Java Developers
Briefly explained essential ideas behind machine learning required to start coding deep learning in Java. How it works, what it can do.
What is project Panama and why is it important for Machine Learning on Java Platform
Panama is the new API for interconnecting Java with native code, which provides Java the ability for faster and easier communication with native libraries required for machine learning applications.
Dukes Choice Award 2018 goes to Apache Net Beans at Code One, San Francisco
Apache Net Beans project has won the most prestigious award for the innovation on Java platform at Oracle Code One Conference in San Francisco.
The Most Significant JSR Award goes to Visual Recognition API, Code One, San Francisco
The most significant JSR Award, which is given by the official organization for Java technology standardization, Java Community Process (JCP) was awarded to Visual Recognition API.
Why Java Will Dominate the Future of Machine Learning, AI, and Big Data
Great presentation by Bernard Traversat, Head of the Java platform development, at Oracle Code One 2018, San Francisco.
Machine Learning For Software Developers in 45 minutes, Code One, San Francisco
Machine Learning for Software Developers in 45 minutes at Oracle Code One conference in San Francisco, by Deep Netts CEO Zoran Sevarac and another Java champion Frank Greco.
Deep Learning and Machine Learning using Deep Netts at Oracle Code One 2018
Our CEO Zoran Sevarac is speaking at two sessions at Oracle Code One 2018 in San Francisco.
Practical Machine Learning at QCon New York 2018
QCon had an amazing machine learning track that presented practitioners from some of the biggest players in industry like Pay Pal and Net Flix, but also provided some real world experiences from building data science and machine learning teams.
Bring high-performance AI into your Java architecture.
Evaluate Deep Netts on your workload. See what Java-native AI can do.