Introducing Gluon — An Easy-to-Use Programming Interface for Flexible Deep Learning

Deep learning just got simpler & faster with the new Gluon API.

  • The first result of this collaboration is the new Gluon interface, an open source library in Apache MXNet that allows developers of all skill levels to prototype, build, and train deep learning models.
  • It brings together the training algorithm and neural network model, thus providing flexibility in the development process without sacrificing performance.
  • Then, when speed becomes more important than flexibility (e.g., when you’re ready to feed in all of your training data), the Gluon interface enables you to easily cache the neural network model to achieve high performance and a reduced memory footprint.
  • For each iteration, there are four steps: (1) pass in a batch of data; (2) calculate the difference between the output generated by the neural network model and the actual truth (i.e., the loss); (3) use to calculate the derivatives of the model’s parameters with respect to their impact on…
  • To learn more about the Gluon interface and deep learning, you can reference this comprehensive set of tutorials, which covers everything from an introduction to deep learning to how to implement cutting-edge neural network models.

Today, AWS and Microsoft announced a new specification that focuses on improving the speed, flexibility, and accessibility of machine learning technology for all developers, regardless of their deep learning framework of choice. The first result of this collaboration is the new Gluon interface, an open source library in Apache MXNet that allows developers of all skill levels to prototype, build, and train deep learning models. This interface greatly simplifies the process of creating deep learning models without sacrificing training speed.
Continue reading “Introducing Gluon — An Easy-to-Use Programming Interface for Flexible Deep Learning”

Machine Learning and Artificial Intelligence: How Computers Learn

What is #ArtificialIntelligence, and how do computers learn? More here:  #iQAsia

  • As more machine learning takes hold, the data requirements will be astounding.
  • “Artificial intelligence is basically where machines make sense, learn, interface with the external world, without human beings having to specifically program it,” said Nidhi Chappell, director of machine learning at Intel.
  • The post Artificial Intelligence and Machine Learning: How Computers Learn appeared first on iQ by Intel .
  • “It is proven that the more data you give to a machine to learn, the more accurate the machine gets at predicting things,” said Chappell, adding that as the complexity of the learning goes up, so do the data requirements to make sense of it.
  • A car could have a computer on board that begins to learn on its own, but having other cars on the road send data to the cloud helps other cars learn too.

From picking our favorite restaurants to correcting global food shortages, artificial intelligence and machine learning already impact our lives.
Continue reading “Machine Learning and Artificial Intelligence: How Computers Learn”

Neural Abstract Machines & Program Induction workshop @ NIPS 2016

1st #nips2016 WS on Neural Abstract Machines & Program Induction (NAMPI)  #dlearn #NLProc #AI

  • The problems of learning procedural behavior and program induction have been studied from different perspectives in many computer science fields such as program synthesis [1], probabilistic programming [2], inductive logic programming [3], reinforcement learning [4], and recently in deep learning.
  • The aim of the NAMPI workshop is to bring together researchers and practitioners from both academia and industry, in the areas of deep learning, program synthesis, probabilistic programming, inductive programming and reinforcement learning, to exchange ideas on the future of program induction with a special focus on neural network models and abstract machines.
  • Machine intelligence capable of learning complex procedural behavior, inducing (latent) programs, and reasoning with these programs is a key to solving artificial intelligence.
  • There have been many success stories in the deep learning community related to learning neural networks capable of using trainable memory abstractions.
  • Neural program induction models like Neural Program-Interpreters [9] and the Neural Programmer [10] have created much excitement in the field, promising induction of algorithmic behavior, and enabling inclusion of programming languages in the processes of execution and induction, while remaining trainable end-to-end.

Read the full article, click here.


@_rockt: “1st #nips2016 WS on Neural Abstract Machines & Program Induction (NAMPI) #dlearn #NLProc #AI”


   _  _____   __  ______  ____
  / |/ / _ | /  |/  / _ \/  _/
 /    / __ |/ /|_/ / ___// /  
/_/|_/_/ |_/_/  /_/_/  /___/ v1.0

Neural Abstract Machines & Program Induction
Workshop at NIPS 2016, Barcelona, Spain


Neural Abstract Machines & Program Induction workshop @ NIPS 2016

Deep Learning Libraries by Language

#DeepLearning Libraries by Language

  • darch package can be used for generating neural networks with many layers (deep architectures).
  • Convnet.js is a Javascript library for training Deep Learning models (mainly Neural Networks) entirely in a browser.
  • DeepLearning is deep learning library, developed with C++ and python.
  • Pylearn2 is a library that wraps a lot of models and training algorithms such as Stochastic Gradient Descent that are commonly used in Deep Learning.
  • Intel® Deep Learning Framework provides a unified framework for Intel® platforms accelerating Deep Convolutional Neural Networks.

Read the full article, click here.


@analyticbridge: “#DeepLearning Libraries by Language”


Source for picture: click here
Python

Theano is a python library for defining and evaluating mathematical expressions with numerical arrays.

Keras is a mi…


Deep Learning Libraries by Language