Weekly BigData & ML Roundup – Mar. 30, 2017

Machine Learning with ARM

In today’s Data Science and Machine Learning world, GPU based acceleration, especially with the ones from Nvidia, is de facto for production level performance. There are many factors contributed to the status quo, and it is hard to deny that solid, consistent SDK support from the company has played a very significant role.

ARM has officially initiated a similar SDK support for hardware acceleration on Machine Learning as recently as 20 days ago. This implies that ARM hardware in your hands such as Raspberry PI will have chances to unlock its full potential in this field. Stay tuned.

Examples

Snaky
A snake game, three versions of AI included, implemented in python, pygame.

Game2vec
TensorFlow implementation of word2vec applied on Steam video games dataset

RNN-Tutorial
Recurrent Neural Networks – A Short TensorFlow Tutorial

Google Magenta
Music and Art Generation with Machine Intelligence

Spark Streaming with Google Cloud by @hereticreader
An example of integrating Spark Streaming with Google Pub/Sub and Google Datastore

Toolset

React.js-Jupyter
Jupytor, powered by React.js

Models

Deep Photo Style Transfer
Code and data for paper “Deep Photo Style Transfer”

Evolution Strategies Starter
Starter code for Evolution Strategies

HTMLAI RNN
Train a RNN (Recurrent Neural Network) to generate valid HTML and CSS templates for websites based on character by character training

Lime
Explaining the predictions of any machine learning classifier

Libraries

ARM Compute Library
The ARM Computer Vision and Machine Learning library is a set of functions optimised for both ARM CPUs and GPUs using SIMD technologies.

Facebook TorchMPI
Implements a message passing interface (MPI) wrapper that makes it easy to do massively parallel computations inside the Torch deep-learning framework.


1000+ tools, frameworks and libraries indexed at PocketCluster Index!
Looking into adding your repo? tweet to @stkim1!

E-mail Subscribtion
Subscribe for upcoming posts!
Join Slack
Join the channel!

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s