EEDSP
20.1K views | +2 today
Follow
 
Scooped by Shiwon Cho
onto EEDSP
Scoop.it!

슈퍼 컴퓨터의 미래, ‘병렬 컴퓨팅’에 묻다

슈퍼 컴퓨터의 미래, ‘병렬 컴퓨팅’에 묻다 | EEDSP | Scoop.it
지난 13일 미국 솔트레이크시티에서는 ‘2012 슈퍼컴퓨팅 학술대회’가 개최됐다. 슈퍼컴퓨팅 학술대회는 매 6개월마다 전 세계...
more...
No comment yet.
EEDSP
Digital Signal Processing, Data Analytics, Big Data, HPC, Deep Learning, GPGPU, Distributed and Parallel Computing
Curated by Shiwon Cho
Your new post is loading...
Your new post is loading...
Scooped by Shiwon Cho
Scoop.it!

Approximating the Softmax for Learning Word Embeddings

Approximating the Softmax for Learning Word Embeddings | EEDSP | Scoop.it
This blog post gives an overview of softmax-based and sampling-based approaches that approximate the softmax layer for learning word embeddings.
more...
No comment yet.
Scooped by Shiwon Cho
Scoop.it!

Deep Learning for Program Synthesis - Microsoft Research

Deep Learning for Program Synthesis - Microsoft Research | EEDSP | Scoop.it
By Rishabh Singh, Jacob Devlin, Abdelrahman Mohamed, and Pushmeet Kohli, Microsoft Research Despite the many advances in computing over the past decades, the actual process of writing computer software has not fundamentally changed — a programmer must manually code the exact algorithmic logic of a program in a step-by-step manner using a specialized programming language. Although programming languages …
more...
No comment yet.
Scooped by Shiwon Cho
Scoop.it!

16 Free and Open-Source Business Intelligence Tools - DZone Big Data

16 Free and Open-Source Business Intelligence Tools - DZone Big Data | EEDSP | Scoop.it
Take a look at some great free and open-source business intelligence tools, including the ELK stack, Helical Insight, BIRT, Jasperreports server, and BIRT.
more...
No comment yet.
Scooped by Shiwon Cho
Scoop.it!

Open Source Deep Learning Frameworks and Visual Analytics

Open Source Deep Learning Frameworks and Visual Analytics | EEDSP | Scoop.it
Deep Learning gets more and more traction. It basically focuses on one section of Machine Learning: Artificial Neural Networks. This article explains why Deep…
more...
No comment yet.
Scooped by Shiwon Cho
Scoop.it!

Machine learning methods (infographic)

Machine learning methods (infographic) | EEDSP | Scoop.it
What’s the right algorithm for the task? Our visual primer shows the most common ones in use and the business problems they solve.
more...
No comment yet.
Scooped by Shiwon Cho
Scoop.it!

Teaching Machines to Draw

Teaching Machines to Draw | EEDSP | Scoop.it
Posted by David Ha, Google Brain Resident Abstract visual communication is a key part of how people convey ideas to one another. From
more...
No comment yet.
Scooped by Shiwon Cho
Scoop.it!

Caffe 2

NVIDIA and Facebook announced Caffe2. 

  

Cafe2: FA New Lightweight, Modular, and Scalable Deep Learning Framework

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

Knowledge extraction from unstructured texts

Knowledge extraction from unstructured texts | EEDSP | Scoop.it
Foreword There is an unreasonable amount of information that can be extracted from what people publicly say on the internet. At Heuritech we use this information to better understand what people want, which products they like and why. This post explains from a scientific point of view what is Knowledge extraction and details a few…
more...
No comment yet.
Scooped by Shiwon Cho
Scoop.it!

Recursive Neural Networks with PyTorch | Parallel Forall

Recursive Neural Networks with PyTorch | Parallel Forall | EEDSP | Scoop.it
PyTorch is a new deep learning framework that makes natural language processing and recursive neural networks easier to implement.
more...
No comment yet.
Scooped by Shiwon Cho
Scoop.it!

Practicing Machine Learning with Optimism

Practicing Machine Learning with Optimism | EEDSP | Scoop.it
Using machine learning to solve real-world problems often presents challenges that weren't initially considered during the development of the machine learning method. This article addresses a few examples of such issues and hopefully provides some suggestions (and inspiration) for how to overcome the challenges using straightforward analyses on the data you already have.
more...
No comment yet.
Scooped by Shiwon Cho
Scoop.it!

Google's dedicated TensorFlow processor, or TPU, crushes Intel, Nvidia in inference workloads - ExtremeTech

Google's dedicated TensorFlow processor, or TPU, crushes Intel, Nvidia in inference workloads - ExtremeTech | EEDSP | Scoop.it
Google has revealed new benchmark results for its custom TensorFlow processing unit, or TPU. In inference workloads, the company's ASI
more...
No comment yet.
Scooped by Shiwon Cho
Scoop.it!

Federated Learning: Collaborative Machine Learning without Centralized Training Data

Federated Learning: Collaborative Machine Learning without Centralized Training Data | EEDSP | Scoop.it
Posted by Brendan McMahan and Daniel Ramage, Research Scientists Standard machine learning approaches require centralizing the trainin
more...
No comment yet.
Scooped by Shiwon Cho
Scoop.it!

Groq This: New AI Chips to Give GPUs a Run for Deep Learning Money

Groq This: New AI Chips to Give GPUs a Run for Deep Learning Money | EEDSP | Scoop.it
CPUs and GPUs, move over. Thanks to recent revelations surrounding Google’s new Tensor Processing Unit (TPU), the computing world appears to be on the cusp
more...
No comment yet.
Scooped by Shiwon Cho
Scoop.it!

What Is the Deep Web? [INFOGRAPHIC]

What Is the Deep Web? [INFOGRAPHIC] | EEDSP | Scoop.it
The Deep Web consists of all the websites that can’t be accessed via search engines. Most people use search engines to navigate the internet and, because of this, will never come across the mysterious, disorganized and occasionally seedy network known as the Deep Web. How Do Search Engines Work? Search engines want to cover as […]
more...
No comment yet.
Scooped by Shiwon Cho
Scoop.it!

Taming Recurrent Neural Networks for Better Summarization | Abigail See

Taming Recurrent Neural Networks for Better Summarization | Abigail See | EEDSP | Scoop.it
This is a blog post about our latest paper, Get To The Point: Summarization with Pointer-Generator Networks, to appear at ACL 2017. Code will be release
more...
No comment yet.
Scooped by Shiwon Cho
Scoop.it!

Deep Neural Network from scratch

Deep Neural Network from scratch | EEDSP | Scoop.it
In this blog post you will learn how a neural network works. All the parts are explained, including the maths. You will also find a python implementation using numpy and a second one using TensorFlow.
more...
No comment yet.
Scooped by Shiwon Cho
Scoop.it!

Emotional chatting machine assesses your emotion and copies it

Emotional chatting machine assesses your emotion and copies it | EEDSP | Scoop.it
Chatbots have never been able to empathize. That looks set to change, thanks to a Chinese team that has built a chatbot capable of conveying specific emotions.
more...
No comment yet.
Scooped by Shiwon Cho
Scoop.it!

A Brief History of CNNs in Image Segmentation: From R-CNN to Mask R-CNN

A Brief History of CNNs in Image Segmentation: From R-CNN to Mask R-CNN | EEDSP | Scoop.it
At Athelas, we use Convolutional Neural Networks(CNNs) for a lot more than just classification! In this post, we’ll see how CNNs can be used, with great results, in image instance segmentation. Ever…
more...
No comment yet.
Scooped by Shiwon Cho
Scoop.it!

A news-analysis NeuralNet learns from a language NeuralNet

A news-analysis NeuralNet learns from a language NeuralNet | EEDSP | Scoop.it
A common way to solve a complex computing task is to chain together specialized components. In data-science this is the pipeline approach. Each component mostly treats the other components as I/O…
more...
No comment yet.
Scooped by Shiwon Cho
Scoop.it!

The Deep Learning Roadmap – Intuition Machine – Medium

The Deep Learning Roadmap – Intuition Machine – Medium | EEDSP | Scoop.it
It just occurred to me, that after a couple of years tracking Deep Learning developments, that nobody has even bothered to create a map of what’s going on! So I quickly decided to come up with a Deep…
more...
No comment yet.
Scooped by Shiwon Cho
Scoop.it!

Anything2Vec, or How Word2Vec Conquered NLP

Anything2Vec, or How Word2Vec Conquered NLP | EEDSP | Scoop.it
This is the website and blog of Yves Peirsman, Natural Language Processing Consultant.
more...
No comment yet.
Scooped by Shiwon Cho
Scoop.it!

Introducing tf-seq2seq: An Open Source Sequence-to-Sequence Framework in TensorFlow

Introducing tf-seq2seq: An Open Source Sequence-to-Sequence Framework in TensorFlow | EEDSP | Scoop.it

An open source seq2seq framework in TensorFlow that makes it easy to experiment with seq2seq models and achieve state-of-the-art results. To that end, we made the tf-seq2seq codebase clean and modular, maintaining full test coverage and documenting all of its functionality.

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

Open Datasets for Deep Learning - Deeplearning4j: Open-source, Distributed Deep Learning for the JVM

Open Datasets for Deep Learning - Deeplearning4j: Open-source, Distributed Deep Learning for the JVM | EEDSP | Scoop.it

Here you’ll find an organized list of interesting, high-quality datasets for machine learning research. We welcome your contributions for curating this list! You can find other lists of such datasets on Wikipedia, for example.

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

A guide to receptive field arithmetic for Convolutional Neural Networks

A guide to receptive field arithmetic for Convolutional Neural Networks | EEDSP | Scoop.it
The receptive field is perhaps one of the most important concepts in Convolutional Neural Networks (CNNs) that deserves more attention from the literature. All of the state-of-the-art object…
more...
No comment yet.