Author Bio Image

Jennifer Myers

Jennifer has 20 years experience leading software engineering at both startups and large companies - spanning networking, security, video and search. She created her first neural networks at Carnegie Mellon in 1987, holds a Ph.D. in Neuroscience from Northwestern where she built recurrent neural networks for her thesis, and she is thrilled to be advancing her original field of study once again.

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
* A new community-contributed Docker image
* Improved error messages when a tensor is created with an invalid shape or reshaped to an incompatible size
* Fix bugs in MultiCost support
* Documentation fixes [#331]

As always, you can grab this release from github at:


Fig. 1: Skip Thought Vector Model

Related Blog Posts

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 your own providers for custom…

Read more

#neon #Release Notes

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 data Eliminate type conversion for FP16…

Read more

#neon #Release Notes

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 compatibility [#191] Support for Pascal…

Read more

#neon #Release Notes