EEDSP
Follow
Find
13.9K views | +24 today
 

From around the web

EEDSP
Digital Signal Processing, Data Analytics, Big Data, HPC, Deep Learning, GPGPU
Curated by Shiwon Cho
Your new post is loading...
Your new post is loading...
Scooped by Shiwon Cho
Scoop.it!

Analysing the Twitter Mentions Network

Analysing the Twitter Mentions Network | EEDSP | Scoop.it
By Douglas Ashton, Consultant One of the big successes of data analytics is the cultural change in how business decisions are being made. There is now wide spread acceptance of the role that data science has to play in decision making.
more...
No comment yet.
Scooped by Shiwon Cho
Scoop.it!

How Twitter Users Can Generate Better Ideas | MIT Sloan Management Review

How Twitter Users Can Generate Better Ideas | MIT Sloan Management Review | EEDSP | Scoop.it
There's a link between the amount of diversity in employees’ Twitter networks and the quality of their ideas.
more...
No comment yet.
Scooped by Shiwon Cho
Scoop.it!

100 Best GitHub: Deep Learning | Meta-Guide.com

100 Best GitHub: Deep Learning | Meta-Guide.com | EEDSP | Scoop.it

This 100 item list represents a search of github for “deep-learning”, Apr 2015.  As of 2015, this is the most popular webpage on the Meta-Guide.com website.

more...
No comment yet.
Scooped by Shiwon Cho
Scoop.it!

Introduction to Neural Machine Translation with GPUs (part 1)

Introduction to Neural Machine Translation with GPUs (part 1) | EEDSP | Scoop.it

Neural machine translation is a recently proposed framework for machine translation based purely on neural networks. This post is the first of a series in which I will explain a simple encoder-deco...

more...
No comment yet.
Scooped by Shiwon Cho
Scoop.it!

Top 10 data mining algorithms in plain English | rayli.net

Top 10 data mining algorithms in plain English | rayli.net | EEDSP | Scoop.it

Today, I’m going to explain in plain English the top 10 most influential data mining algorithms as voted on by 3 separate panels in this 2007 survey paper.

more...
No comment yet.
Scooped by Shiwon Cho
Scoop.it!

Demistifying LSTM Neural Networks

Demistifying LSTM Neural Networks | EEDSP | Scoop.it
Given its wide applicability to real-world tasks, deep learning has attracted the attention of a wide audience of interested technologists, investors, and spectators. While the most celebrated results use feedforward convolutional neural networks (convnets) to solve problems in computer vision,...
more...
No comment yet.
Scooped by Shiwon Cho
Scoop.it!

Machine Learning Algorithm Cheat Sheet | Azure

Machine Learning Algorithm Cheat Sheet | Azure | EEDSP | Scoop.it
A downloadable machine learning algorithm cheat sheet that can help you figure out how to choose a machine learning algorithm.
more...
No comment yet.
Scooped by Shiwon Cho
Scoop.it!

nagadomi/waifu2x

nagadomi/waifu2x | EEDSP | Scoop.it

 

waifu2x: Super-Resolution for anime/fan-art using Deep Convolutional Neural Networks

more...
No comment yet.
Scooped by Shiwon Cho
Scoop.it!

CS231n Convolutional Neural Networks for Visual Recognition

CS231n Convolutional Neural Networks for Visual Recognition | EEDSP | Scoop.it
Course materials and notes for Stanford class CS231n: Convolutional Neural Networks for Visual Recognition.
more...
No comment yet.
Scooped by Shiwon Cho
Scoop.it!

ferd.ca -> Lessons Learned while Working on Large-Scale Server Software

ferd.ca -> Lessons Learned while Working on Large-Scale Server Software | EEDSP | Scoop.it

This text is an attempt to recount some of the hard-earned lessons I have ended up learning, sometimes indirectly, but often personally. Everything is terrible, but our job still is to build something solid and usable on top of that everything. What we build adds to that 'everything', makes it bigger, more terrible.

more...
No comment yet.
Scooped by Shiwon Cho
Scoop.it!

Choosing R or Python for data analysis? An infographic

Choosing R or Python for data analysis? An infographic | EEDSP | Scoop.it
Wondering whether you should use R or Python for your next data analysis post? Check our infographic "Data Science Wars: R vs Python".
more...
No comment yet.
Scooped by Shiwon Cho
Scoop.it!

Google Cloud Bigtable

Google Cloud Bigtable | EEDSP | Scoop.it

Cloud implementation of Bigtable. 

Google Cloud Bigtable offers you a fast, fully managed, massively scalable NoSQL database service that's ideal for web, mobile, and Internet of Things applications requiring terabytes to petabytes of data. Unlike comparable market offerings, Cloud Bigtable doesn't require you to sacrifice speed, scale, or cost efficiency when your applications grow. Cloud Bigtable has been battle-tested at Google for more than 10 years—it's the database driving major applications such as Google Analytics and Gmail.

more...
No comment yet.
Scooped by Shiwon Cho
Scoop.it!

Elements of Scale: Composing and Scaling Data Platforms - ben stopford

Elements of Scale: Composing and Scaling Data Platforms - ben stopford | EEDSP | Scoop.it
This transcribed talk explores a range of data platforms through a lens of basic hardware and software tradeoffs.
more...
No comment yet.
Scooped by Shiwon Cho
Scoop.it!

Architectural Patterns for Near Real-Time Data Processing with Apache Hadoop

Architectural Patterns for Near Real-Time Data Processing with Apache Hadoop | EEDSP | Scoop.it

Evaluating which streaming architectural pattern is the best match to your use case is a precondition for a successful production deployment.

 


more...
No comment yet.
Scooped by Shiwon Cho
Scoop.it!

Origami Robot Folds Itself Up, Does Cool Stuff, Dissolves Into Nothing

Origami Robot Folds Itself Up, Does Cool Stuff, Dissolves Into Nothing | EEDSP | Scoop.it
Tiny self-folding magnetically actuated robot creates itself when you want it, disappears when you don
more...
No comment yet.
Scooped by Shiwon Cho
Scoop.it!

How Stephen Wolfram’s image-recognition tool performs against 5 alternatives

How Stephen Wolfram’s image-recognition tool performs against 5 alternatives | EEDSP | Scoop.it
To get a feel for the power of the new Wolfram technology, I put it up against other image-recognition systems.
more...
No comment yet.
Scooped by Shiwon Cho
Scoop.it!

PNNL: Energy Star

PNNL: Energy Star | EEDSP | Scoop.it

To improve overall energy efficiency and performance on future exascale computing systems, scientists from PNNL; University of California, Riverside; and Marquette University examined some advanced high-performance computing systems and determined undervolting that also leverages existing mainstream resilience techniques at scale to reduce power consumption improved system failure rates. The undervolting method does not require modifying existing hardware or using pre-production machines and has shown positive results toward achieving a cost-efficient, energy-savings implementation for the HPC field. The paper documenting this first-of-its-kind work, Investigating the Interplay between Energy Efficiency and Resilience in High Performance Computing, will be presented during the IPDPS 2015 conferences technical program.

more...
No comment yet.
Scooped by Shiwon Cho
Scoop.it!

Stanford University CS231n: Convolutional Neural Networks for Visual Recognition

Stanford University CS231n: Convolutional Neural Networks for Visual Recognition | EEDSP | Scoop.it

We present a model that generates natural language descriptions of images and their regions. Our approach leverages datasets of images and their sentence descriptions to learn about the inter-modal correspondences between language and visual data. Our alignment model is based on a novel combination of Convolutional Neural Networks over image regions, bidirectional Recurrent Neural Networks over sentences, and a structured objective that aligns the two modalities through a multimodal embedding. We then describe a Multimodal Recurrent Neural Network architecture that uses the inferred alignments to learn to generate novel descriptions of image regions. We demonstrate that our alignment model produces state of the art results in retrieval experiments on Flickr8K, Flickr30K and MSCOCO datasets. We then show that the generated descriptions significantly outperform retrieval baselines on both full images and on a new dataset of region-level annotations.

more...
No comment yet.
Scooped by Shiwon Cho
Scoop.it!

Tachyon Overview - Tachyon 0.6.4 Documentation

Tachyon is a memory-centric distributed storage system enabling reliable data sharing at memory-speed across cluster frameworks, such as Spark and MapReduce. It achieves high performance by leveraging lineage information and using memory aggressively. Tachyon caches working set files in memory, thereby avoiding going to disk to load datasets that are frequently read. This enables different jobs/queries and frameworks to access cached files at memory speed.
more...
No comment yet.
Scooped by Shiwon Cho
Scoop.it!

Deep Learning Pioneer Pushing GPU Neural Network Limits

Deep Learning Pioneer Pushing GPU Neural Network Limits | EEDSP | Scoop.it
Back in the late 1980s, while working in the Adaptive Systems Research Department at AT&T Bell Labs, deep leaning pioneer, Yann LeCun, was just startin
more...
No comment yet.
Scooped by Shiwon Cho
Scoop.it!

Implementing a Programming Language in C - Part 1 - bread-man’s blog

Implementing a Programming Language in C - Part 1 - bread-man’s blog | EEDSP | Scoop.it
Introduction You can find the GitHub repository for this project here. All the source code will be updated as we go on with the project, so feel free …
more...
No comment yet.
Scooped by Shiwon Cho
Scoop.it!

MongoDB + RocksDB: Writing so Fast it Makes Your Head Spin

MongoDB + RocksDB: Writing so Fast it Makes Your Head Spin | EEDSP | Scoop.it

Last week, I talked about how we set up Flashback to start benchmarking MongoDB 3.0 and highlighted the insane storage efficiencies achieved with both RocksDB and WiredTiger. As a recap, the amount of storage used dropped by more than 10x when importing a production replica set into either RocksDB or WiredTiger. This next post will dive into how MongoDB with RocksDB performs against production workloads. We initially focused on latencies, which were broken down by operation type. For comparison,

more...
No comment yet.
Scooped by Shiwon Cho
Scoop.it!

SparkCL: A Unified Programming Framework for Accelerators on Heterogeneous Clusters

SparkCL: A Unified Programming Framework for Accelerators on Heterogeneous Clusters | EEDSP | Scoop.it
We introduce SparkCL, an open source unified programming framework based on Java, OpenCL and the Apache Spark framework. The motivation behind this work is to bring unconventional compute cores suc...
more...
No comment yet.