TensorFlow
An open-source software library for Machine Intelligence.
TensorFlow™ is an open-source software library, which was
originally developed by researchers and engineers working on the Google
Brain Team. TensorFlow is for numerical computation using data flow
graphs. Nodes in the graph represent mathematical operations, while the
graph edges represent the multidimensional data arrays (tensors)
communicated between them. The flexible architecture allows you to
deploy computation to one or more CPUs or GPUs in a desktop, server, or
mobile device with a single API.
TensorFlow provides multiple APIs. The lowest level API —
TensorFlow Core — provides you with complete programming control. The
higher level APIs are built on top of TensorFlow Core. These higher
level APIs are typically easier to learn and use than TensorFlow Core.
In addition, the higher level APIs make repetitive tasks easier and more
consistent between different users. A high-level API like tf.estimator
helps you manage data sets, estimators, training, and inference.
The central unit of data in TensorFlow is the
tensor. A tensor consists of a set of primitive values shaped into an array of any number of dimensions. A tensor's
rank is its number of dimensions.
A few Google applications using tensor flow are:
RankBrain: A large-scale deployment of deep neural nets for search ranking on www.google.com
Inception Image Classification Model: Baseline
model and follow-on research into highly accurate computer vision
models, starting with the model that won the 2014 Imagenet image
classification challenge
SmartReply: Deep LSTM model to automatically generate email responses
Massively Multitask Networks for Drug Discovery: A deep neural network model for identifying promising drug candidates by
Google in association with Stanford University.
On-Device Computer Vision for OCR: On-device computer vision model to do optical character recognition to enable real-time translation
Useful Links
Tensorflow home
GitHub
Getting started
Apache SystemML
An optimal workplace for machine learning using big data.
SystemML, the machine-learning technology created at IBM,
has reached one of the top-level project status at the Apache Software
Foundation and it’s a flexible, scalable, machine learning system.
Important characteristics are:
Algorithm customizability via R-like and Python-like languages.
Multiple execution modes, including Spark MLContext, Spark
Batch, Hadoop Batch, Standalone, and JMLC (Java Machine Learning
Connector).
Automatic optimization based on data and cluster characteristics to ensure both efficiency and scalability.
SystemML considered as SQL for Machine learning. Latest
version (1.0.0) of SystemML supports: Java 8+, Scala 2.11+, Python
2.7/3.5+, Hadoop 2.6+, and Spark 2.1+.
It can be run on top of Apache Spark, where it automatically
scales your data line by line, determining whether your code should be
run on the driver or an Apache Spark cluster. Future SystemML
developments include additional deep learning with GPU capabilities such
as importing and running neural network architectures and pre-trained
models for training.
Java Machine Learning Connector (JMLC) for SystemML
The Java Machine Learning Connector (JMLC) API is a
programmatic interface for interacting with SystemML in an embedded
fashion. The primary purpose of JMLC is as a scoring API, where your
scoring function is expressed using SystemML’s DML (Declarative Machine
Learning) language. In addition to scoring, embedded SystemML can be
used for tasks such as unsupervised learning (for example, clustering)
in the context of a larger application running on a single machine.
Useful Links
SystemML home
GitHub
Caffe
A deep learning framework made with expression, speed, and modularity in mind.
The Caffe project was initiated by Yangqing Jia during his
Ph.D. at UC Berkeley and then later developed by Berkeley AI Research
(BAIR) and by community contributors. It mostly focusses on
convolutional networks for computer vision applications. Caffe is a
solid and popular choice for computer vision-related tasks and you can
download many successful models made by Caffe users from the Caffe Model
Zoo (link below) for out-of-the-box use.
Caffe Advantages
Expressive architecture encourages
application and innovation. Models and optimization are defined by
configuration without hard-coding. Switch between CPU and GPU by setting
a single flag to train on a GPU machine then deploy to commodity
clusters or mobile devices.
Extensible code fosters active development.
In Caffe’s first year, it has been forked by over 1,000 developers and
had many significant changes contributed back.
Speed makes Caffe perfect for research experiments and industry deployment. Caffe can process
over 60M images per day with a single NVIDIA K40 GPU.
Community: Caffe already powers academic
research projects, startup prototypes, and even large-scale industrial
applications in vision, speech, and multimedia.
Useful Links
Caffe home
GitHub
Caffe user group
Tutorial presentation of the framework and a full-day crash course
Caffe Model Zoo
Apache Mahout
A distributed linear algebra framework and mathematically expressive Scala DSL
Mahout was designed to let mathematicians, statisticians,
and data scientists quickly implement their own algorithms. Apache Spark
is the recommended out-of-the-box distributed backend or can be
extended to other distributed backends.
Mathematically Expressive Scala DSL
Support for Multiple Distributed Backends (including Apache Spark)
Modular Native Solvers for CPU/GPU/CUDA Acceleration
Apache Mahout currently implements areas including Collaborative filtering (CF), Clustering and Categorization
Features/Applications
Taste CF. Taste is an open-source project for CF
(collaborative filtering) started by Sean Owen on SourceForge and
donated to Mahout in 2008.
Several Map-Reduce enabled clustering implementations including k-Means, fuzzy k-Means, Canopy, Dirichlet, and Mean-Shift.
Distributed Naive Bayes and Complementary Naive Bayes classification implementations.
Distributed fitness function capabilities for evolutionary programming.
Matrix and vector libraries.
Examples of all of the above algorithms.
Useful Links
Mahout home
GitHub
Intro to Mahout by Grant Ingersoll
OpenNN
An open-source class library written in C++, which implements neural networks.
OpenNN (Open Neural Networks Library) was formerly known as
Flood is based on the Ph.D. thesis of R. Lopez, "Neural Networks for
Variational Problems in Engineering," at Technical University of
Catalonia, 2008.
OpenNN implements data mining methods as a bundle of
functions. These can be embedded in other software tools using an
application programming interface (API) for the interaction between the
software tool and the predictive analytics tasks. The main advantage of
OpenNN is its high performance. It is developed in C++ for better memory
management and higher processing speed and implements CPU
parallelization by means of OpenMP and GPU acceleration with CUDA.
The package comes with unit testing, many examples, and
extensive documentation. It provides an effective framework for the
research and development of neural networks algorithms and applications.
Neural Designer is a professional predictive analytics tool that uses
OpenNN, which means that the neural engine of Neural Designer has been
built using OpenNN.
OpenNN has been designed to learn from both datasets and mathematical models.
Datasets
Function regression.
Pattern recognition.
Time series prediction.
Mathematical Models
Optimal control.
Optimal shape design.
Datasets and Mathematical Models
Inverse problems.
Useful Links
OpenNN home
OpenNN Artelnics GitHub
Neural Designer
Torch
An open-source machine learning library, a scientific
computing framework, and a script language based on the Lua programming
language.
- a powerful N-dimensional array
- lots of routines for indexing, slicing, transposing, …
- amazing interface to C, via LuaJIT
- linear algebra routines
- neural network, and energy-based models
- numeric optimization routines
- Fast and efficient GPU support
- Embeddable, with ports to iOS and Android backends
Torch is used by the Facebook AI Research Group, IBM,
Yandex, and the Idiap Research Institute. It has been extended for use
on Android and iOS and has been used to build hardware implementations
for data flows like those found in neural networks.
Facebook has released a set of extension modules as open source software.
PyTorch is an open-source machine learning library for
Python, used for applications such as natural language processing. It is
primarily developed by Facebook's artificial intelligence research
group, and Uber's "Pyro" software for probabilistic programming is built
upon it.
Useful Links
Torch Home
GitHub
Neuroph
An object-oriented neural network framework written in Java.
Neuroph can be used to create and train neural networks in
Java programs. Neuroph provides Java class library as well as GUI tool
easyNeurons for creating and training neural networks. Neuroph is
lightweight Java neural network framework to develop common neural
network architectures. It contains a well designed, open-source Java
library with a small number of basic classes that correspond to basic NN
concepts. It also has nice GUI neural network editor to quickly create
Java neural network components. It has been released as open source
under the Apache 2.0 license.
Neuroph's core classes correspond to basic neural network
concepts like artificial neuron, neuron layer, neuron connections,
weight, transfer function, input function, learning rule, etc. Neuroph
supports common neural network architectures such as Multilayer
perceptron with Backpropagation, Kohonen and Hopfield networks. All
these classes can be extended and customized to create custom neural
networks and learning rules. Neuroph has built-in support for image
recognition.
Useful Links
Neuroph Home
GitHub
Deeplearning4j
The first commercial-grade, open-source, distributed deep-learning library written for Java and Scala.
Deeplearning4j aims to be cutting-edge plug and play and
more convention than configuration, which allows for fast prototyping
for non-researchers.
DL4J is customizable at scale.
DL4J can import neural net models from most major
frameworks via Keras, including TensorFlow, Caffe and Theano, bridging
the gap between the Python ecosystem and the JVM with a cross-team
toolkit for data scientists, data engineers and DevOps. Keras is
employed as Deeplearning4j's Python API.
Machine learning models are served in production with Skymind's model server.
Features
- Distributed CPUs and GPUs
- Java, Scala and Python APIs
- Adapted for micro-service architecture
- Parallel training via iterative reduce
- Scalable on Hadoop
- GPU support for scaling on AWS
Libraries:
- Deeplearning4J: Neural Net Platform
- ND4J: Numpy for the JVM
- DataVec: Tool for Machine Learning ETL Operations
- JavaCPP: The Bridge Between Java and Native C++
- Arbiter: Evaluation Tool for Machine Learning Algorithms
- RL4J: Deep Reinforcement Learning for the JVM
Mycroft
Claiming as the world’s first open-source assistant and may
be used in anything from a science project to an enterprise software
application.
Mycroft runs anywhere — on a desktop computer, inside an
automobile, or on a Raspberry Pi. This is open source software which can
be freely remixed, extended, and improved. Mycroft may be used in
anything from a science project to an enterprise software application.
OpenCog
OpenCog is a project that aims to build an open-source artificial intelligence framework
OpenCog is a diverse assemblage of cognitive algorithms,
each embodying their own innovations — but what makes the overall
architecture powerful is its careful adherence to the principle of
cognitive synergy. OpenCog was originally based on the release in 2008
of the source code of the proprietary "Novamente Cognition Engine" (NCE)
of Novamente LLC. The original NCE code is discussed in the PLN book
(ref below). Ongoing development of OpenCog is supported by Artificial
General Intelligence Research Institute (AGIRI), the Google Summer of
Code project, and others.
- A graph database that holds terms, atomic formulas,
sentences and relationships as hypergraphs; giving them a probabilistic
truth-value interpretation, dubbed the AtomSpace.
- A satisfiability modulo theories solver, built in as a
part of a generic graph query engine, for performing graph and
hypergraph pattern matching (isomorphic subgraph discovery).
- An implementation of a probabilistic reasoning engine based on probabilistic logic networks (PLN).
- A probabilistic genetic program evolver called
Meta-Optimizing Semantic Evolutionary Search, or MOSES, originally
developed by Moshe Looks who is now employed at Google.
- An attention allocation system based on economic theory, ECAN.
- An embodiment system for interaction and learning within virtual worlds based in part on OpenPsi and Unity.
- A natural language input system consisting of Link
Grammar and RelEx, both of which employ AtomSpace-like representations
for semantic and syntactic relations.
- A natural language generation system called SegSim, with implementations NLGen and NLGen2.
- An implementation of Psi-Theory for handling emotional states, drives, and urges, dubbed OpenPsi.
- Interfaces to Hanson Robotics robots, including emotion modeling via OpenPsi.
Useful Links
OpenCog Home
GitHub
OpenCog Wiki
Source: https://dzone.com
Building a baseline statistical phrase MT system
The 
Corpora
Posts
