Building Skip-Thought Vectors for Document Understanding

The idea of converting natural language processing (NLP) into a problem of vector space mathematics using deep learning models has been around since 2013. A word vector, from word2vec [1], uses a string of numbers to represent a word’s meaning as it relates to other words, or its context, through [...]

By | Thursday, January 5, 2017|Developer|

neon v1.8.0 released!

Highlights from this release include:  * Skip Thought Vectors example * Dilated convolution support * Nesterov Accelerated Gradient option to SGD optimizer * MultiMetric class to allow wrapping Metric classes * Support for serializing and deserializing encoder-decoder models * Allow specifying the number of time steps to evaluate during beam search * [...]

By | Wednesday, December 28, 2016|Developer|

End-to-end speech recognition with neon

By: Anthony Ndirango and Tyler Lee Speech is an intrinsically temporal signal. The information-bearing elements present in speech evolve over a multitude of timescales. The fine changes in air pressure at rates of hundreds to thousands of hertz convey information about the speakers, their location, and help us separate them from a [...]

By | Wednesday, December 7, 2016|Developer|

neon v1.7.0 released!

Highlights from this release include:  Update Data Loader to aeon for flexible, multi-threaded data loading and transformations. More information can be found in the docs, but in brief, aeon: provides an easy interface to adapt existing models to your own, custom, datasets supports images, video and audio and is easy to extend with [...]

By | Monday, November 21, 2016|Developer|

Preview Release: Intel® Nervana™ Graph

The field of deep learning is moving at a rapid pace.  Practitioners need tools that are flexible enough to keep up. Theano popularized the notion of computational graphs as a powerful abstraction, and more recently, TensorFlow iterated on that concept. Together, they demonstrate some first steps in unlocking the [...]

By | Thursday, November 17, 2016|Developer|

Accelerating Neural Networks with Binary Arithmetic

At Nervana we are deeply interested in algorithmic and hardware improvements for speeding up neural networks. One particularly exciting area of research is in low precision arithmetic. In this blog post, we highlight one particular class of low precision networks named binarized neural networks (BNNs), the fundamental concepts underlying this [...]

By | Wednesday, October 12, 2016|Developer|

neon v1.6.0 released!

Highlights from this release include:  Faster RCNN model Sequence to Sequence container and char_rae recurrent autoencoder model Reshape Layer that reshapes the input [#221] Pip requirements in requirements.txt updated to latest versions [#289] Remove deprecated data loaders and update docs Use NEON_DATA_CACHE_DIR envvar as archive dir to store DataLoader ingested [...]

By | Wednesday, September 21, 2016|Developer|

Simplified ncloud syntax and other improvements to Nervana Cloud

Nervana Cloud is a full-stack hosted platform for deep learning that enables businesses to develop and deploy high-accuracy deep learning solutions at a fraction of the cost of building their own infrastructure and data science teams. We recently updated Nervana Cloud’s ncloud command-line interface (CLI) syntax to support subcommands and [...]

By | Thursday, September 8, 2016|Developer, Product|

neon v1.5 released!

We’re excited to release neon v1.5 with Python 2 and Python 3 support, support for Pascal GPUs (GTX 1080) and performance enhancements such as persistent RNN kernels (based on the paper by Greg Diamos at Baidu), bringing a 12x performance gain compared to v1.4.0. Highlights from this release include: Python2/Python3 [...]

By | Friday, July 1, 2016|Developer|