Popularity

2.3

Growing

Activity

6.8

Stars 62

Watchers 4

Forks 1

Last Commit 2 months ago

Programming language: Java

License: MIT License

Tags: Machine Learning Projects

Neureka alternatives and similar libraries

Based on the "Machine Learning" category.
Alternatively, view neureka alternatives based on common mentions on social networks and blogs.

m2cgen

7.3 0.0 Neureka VS m2cgen

Transform ML models into a native code (Java, C, Python, Go, JavaScript, Visual Basic, C#, R, PowerShell, PHP, Dart, Haskell, Ruby, F#, Rust) with zero dependencies
Siddhi

7.1 6.7 Neureka VS Siddhi

Stream Processing and Complex Event Processing Engine

InfluxDB - Power Real-Time Data Analytics at Scale

Get real-time insights from all types of time series data with InfluxDB. Ingest, query, and analyze billions of data points in real-time with unbounded cardinality.

Promo www.influxdata.com

Tribuo

6.1 5.3 Neureka VS Tribuo

Tribuo - A Java machine learning library
oj! Algorithms

5.0 8.3 Neureka VS oj! Algorithms

oj! Algorithms
Synapses

2.5 0.0 Neureka VS Synapses

A group of neural-network libraries for functional and mainstream languages
Intelligent java

2.4 3.8 Neureka VS Intelligent java

Integrate with the latest language models, image generation, speech, and deep learning frameworks like ChatGPT, DALL·E, and Cohere using few java lines.

Do you think we are missing an alternative of Neureka or a related project?

Add another 'Machine Learning' Library

Popular Comparisons

oj! Algorithms

vs

Tribuo

README

:cyclone: NEUREKA :cyclone:

A platform independent tensor library written in Java.

OpenCL accelerated nd-arrays / tensors for Java, Kotlin, Groovy, Scala, Jython, JRuby...

Visit Neurekas homepage for more information!
Try out the latest release: neureka.jar

Current Build	Code Coverage	Version	Codacy	Licence	Size

:hammer_and_wrench: Features

dynamic computation graph
auto differentiation (forwards/backwards)
nd-convolution
nd-broadcasting
flexible tensor indexing and slicing
seeding
labeling
loading and saving as jpg/idx files

Take a quick look:

[Neureka with Java](docs/markdown/java_example.md) :coffee:
[Neureka with Groovy](docs/markdown/groovy_example.md) :star:

:robot: Tech

Dynamic Autograd : Recording the Computation-Graph ###

Neureka trains your neural network using a computation graph recorder.

This is contrary to the approaches found in other frameworks such as TensorFlow, Theano, Caffe, and CNTK which require the definition of a computation graph ahead of time. This means a developer has to build a neural network structure which cannot change during runtime.

Neureka, uses the recorded computation graph in order to apply a technique called reverse-mode auto-differentiation, which allows your network structure to change during runtime arbitrarily with zero lag or overhead. This powerful feature has been inspired by PyTorch:

[Motivation](docs/markdown/motivation.md) :fire:

Main-Package Overview

Package	Description
[neureka](src/main/java/neureka/README.md)	the root package containing the tensor class and the following sub-packages
[neureka.devices](src/main/java/neureka/devices/README.md)	a sub-package which enables cross platform acceleration (`OpenCLDevice`) and tensor persistence (`FileDevice`)
[neureka.calculus](src/main/java/neureka/calculus/README.md)	a sub-package containing collections of functions and the ability to create custom ones
[neureka.optimization](src/main/java/neureka/optimization/README.md)	a sub-package for weight-gradient optimization
[neureka.autograd](src/main/java/neureka/autograd/README.md)	the guts of Neurekas autograd system
[neureka.backend](src/main/java/neureka/backend/README.md)	the backend containing both a consistent API and a standard implementation

Getting started with Apache Maven:

<dependency>
  <groupId>com.github.gleethos</groupId>
  <artifactId>neureka</artifactId>
  <version>0.6.0</version>
</dependency>

Getting started with Gradle:

Groovy DSL:

implementation 'com.github.gleethos:neureka:0.6.0'

Kotlin DSL:

implementation("com.github.gleethos:neureka:0.6.0")

...or alternatively:

Add jitpack in your root build.gradle at the end of repositories: allprojects { repositories { //... maven { url 'https://jitpack.io' } } }
Add Neureka as dependency: dependencies { implementation 'com.github.Gleethos:neureka:v0.6.0' }

Getting started with Groovy Grape:

@GrabResolver(name = 'jitpack.io', root = 'https://jitpack.io')
@Grab('com.github.Gleethos:neureka:v0.6.0')

import neureka.*

:rocket: Building from source

Execute the following:

 gradlew build

Tests:

 gradlew check

Jar file:

 gradlew jar

Min-jar file:

 gradlew proguard

:mount_fuji: Dependencies

OpenCL 2.^ - (JOCL binding)
SLF4J 1.7.+ - (Logging API allowing for custom backends)

:book: Documentation

:microscope: Testing & Specification :scroll:

BDD & living documentation with Spock!
Yes ! Readable html test reports. Check it out!!

:seedling: Development - - -

Want to contribute? Don't worry:

There is plenty of developer friendly highly readable living documentation to go through which explains the inner and outer workings of this project very well!

And feedback is always greatly appreciated!