EEDSP
20.6K views | +0 today
Follow
 
Scooped by Shiwon Cho
onto EEDSP
Scoop.it!

X-47B demonstrator makes first catapult launch

X-47B demonstrator makes first catapult launch | EEDSP | Scoop.it
The X-47B Unmanned Combat Air System (UCAS) demonstrator has taken yet another step on the path towards unmanned aircraft operating amongst piloted aircraft...
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!

A Meta-analysis of DAVIS-2017 Video Object Segmentation Challenge

A Meta-analysis of DAVIS-2017 Video Object Segmentation Challenge | EEDSP | Scoop.it
In the previous post: Video Object Segmentation — The Basics, we’ve gone through the problem definition of Video Object Segmentation, its metrics and nuances. Then we’ve covered the two main…
more...
No comment yet.
Scooped by Shiwon Cho
Scoop.it!

Introducing: Unity Machine Learning Agents – Unity Blog

Introducing: Unity Machine Learning Agents – Unity Blog | EEDSP | Scoop.it
Our two previous blog entries implied that there is a role games can play in driving the development of Reinforcement Learning algorithms. As the world’
more...
No comment yet.
Scooped by Shiwon Cho
Scoop.it!

Four deep learning trends from ACL 2017 | Abigail See

Four deep learning trends from ACL 2017 | Abigail See | EEDSP | Scoop.it
In this two-part post, I describe four broad research trends that I observed at the conference (and its co-located events) through papers, presentations and discussions. The content is guided entirely by my own research interests; accordingly it’s mostly focused on deep learning, sequence-to-sequence models, and adjacent topics. This first part will explore two inter-related themes: linguistic structure and word representations.
more...
No comment yet.
Scooped by Shiwon Cho
Scoop.it!

Deep Learning with Intel’s BigDL and Apache Spark - Cloudera Engineering Blog

Deep Learning with Intel’s BigDL and Apache Spark - Cloudera Engineering Blog | EEDSP | Scoop.it
Cloudera recently published a blog post on how to use Deeplearning4J (DL4J) along with Apache Hadoop and Apache Spark to get state-of-the-art results on an image recognition task. Continuing on a similar stream of work, in this post we discuss a viable alternative that is specifically designed to be used with Spark, and data available in Spark and Hadoop clusters via a Scala or Python API.
The Deep Learning landscape is still evolving. Read more
more...
No comment yet.
Scooped by Shiwon Cho
Scoop.it!

Transformer: A Novel Neural Network Architecture for Language Understanding

Transformer: A Novel Neural Network Architecture for Language Understanding | EEDSP | Scoop.it
Posted by Jakob Uszkoreit, Software Engineer, Natural Language Understanding Neural networks, in particular recurrent neural networks
more...
No comment yet.
Scooped by Shiwon Cho
Scoop.it!

Distributed TensorFlow and the hidden layers of engineering work

Distributed TensorFlow and the hidden layers of engineering work | EEDSP | Scoop.it
By Brad Svee, Staff Cloud Solutions Architect With all the buzz around Machine Learning as of late, it’s no surprise that companies ar
more...
No comment yet.
Scooped by Shiwon Cho
Scoop.it!

NVIDIA Deep Learning SDK Update for Volta Now Available – NVIDIA Developer News Center

NVIDIA Deep Learning SDK Update for Volta Now Available – NVIDIA Developer News Center | EEDSP | Scoop.it
At GTC 2017, NVIDIA announced Volta optimized updates to the NVIDIA Deep Learning SDK. Today, we’re making these updates available as free downloads to members of the NVIDIA Developer Program. Deep learning frameworks using NVIDIA cuDNN 7 and NCCL 2 can take advantage of new features and performance benefits of the Volta architecture.
more...
No comment yet.
Scooped by Shiwon Cho
Scoop.it!

From Microservices to Service Blocks using Spring Cloud Function and AWS Lambda

From Microservices to Service Blocks using Spring Cloud Function and AWS Lambda | EEDSP | Scoop.it
This blog post will introduce you to building service block architectures using Spring Cloud Function and AWS Lambda.
more...
No comment yet.
Scooped by Shiwon Cho
Scoop.it!

Introduction to reinforcement learning and OpenAI Gym

Introduction to reinforcement learning and OpenAI Gym | EEDSP | Scoop.it

Those interested in the world of machine learning are aware of the capabilities of reinforcement-learning-based AI. The past few years have seen many breakthroughs using reinforcement learning (RL). The company DeepMind combined deep learning with reinforcement learning to achieve above-human results on a multitude of Atari games and, in March 2016, defeated Go champion Le Sedol four games to one. Though RL is currently excelling in many game environments, it is a novel way to solve problems that require optimal decisions and efficiency, and will surely play a part in machine intelligence to come.

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

Alice and Bob: The World’s Most Famous Cryptographic Couple

A History of Alice and Bob, by Quinn DuPont and Alana Cattapan (created 2017).
more...
No comment yet.
Scooped by Shiwon Cho
Scoop.it!

Pruning deep neural networks to make them fast and small

Pruning deep neural networks to make them fast and small | EEDSP | Scoop.it

PyTorch implementation of [1611.06440 Pruning Convolutional Neural Networks for Resource Efficient Inference]. TL;DR: By using pruning a VGG-16 based Dogs-vs-Cats classifier is made x3 faster and x4 smaller. Pruning neural networks is an old idea going back to 1990 (with Yan Lecun’s optimal brain damage work) and before. The idea is that among the many parameters in the network, some are redundant and don’t contribute a lot to the output. If you could rank the neurons in the network according to how much they contribute, you could then remove the low ranking neurons from the network, resulting in a smaller and faster network.

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

Understanding Recurrent Neural Networks: The Preferred Neural Network for Time-Series Data

Understanding Recurrent Neural Networks: The Preferred Neural Network for Time-Series Data | EEDSP | Scoop.it
Artificial intelligence has been in the background for decades, kicking up dust in the distance, but never quite arriving. Well that era is over. In 2017, AI has broken through the dust cloud and…
more...
No comment yet.
Scooped by Shiwon Cho
Scoop.it!

State-of-the-art neural coreference resolution for chatbots

State-of-the-art neural coreference resolution for chatbots | EEDSP | Scoop.it
At Hugging Face � we work on the most amazing and challenging subset of natural language: millennial language. Full of uncertainties �, implicit references �, emojis �, jokes � and constantly…
more...
No comment yet.
Scooped by Shiwon Cho
Scoop.it!

10 Common Software Architectural Patterns in a nutshell

10 Common Software Architectural Patterns in a nutshell | EEDSP | Scoop.it
Ever wondered how large enterprise scale systems are designed? Before major software development starts, we have to choose a suitable architecture that will provide us with the desired functionality…
more...
No comment yet.
Scooped by Shiwon Cho
Scoop.it!

Exploring K-Means in Python, C++ and CUDA

Exploring K-Means in Python, C++ and CUDA | EEDSP | Scoop.it

 Implementations of K-Means in three different environments: C++, CUDA and Python

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

Sound Pattern Recognition with Python – Adilson Neto – Medium

Sound Pattern Recognition with Python – Adilson Neto – Medium | EEDSP | Scoop.it
As you can probably tell from the title in this post I will be toying around with python and sound to detect sound patterns. More specifically, knocking patterns, like the ones you make when you…
more...
No comment yet.
Scooped by Shiwon Cho
Scoop.it!

An Intuitive Guide to Deep Network Architectures – Towards Data Science – Medium

An Intuitive Guide to Deep Network Architectures – Towards Data Science – Medium | EEDSP | Scoop.it
Understanding the theory and intuition behind ResNet, Inception, and Xception
more...
No comment yet.
Scooped by Shiwon Cho
Scoop.it!

How does physics connect to machine learning? – Jaan Altosaar

How does physics connect to machine learning? – Jaan Altosaar | EEDSP | Scoop.it
Did Richard Feynman help seed a key machine learning technique in the 60s?
more...
No comment yet.
Scooped by Shiwon Cho
Scoop.it!

人工知能(AI)を実現するディープラーニング(深層学習)の統合開発環境Neural Network Consoleを公開

人工知能(AI)を実現するディープラーニング(深層学習)の統合開発環境Neural Network Consoleを公開 | EEDSP | Scoop.it

ソニーはディープラーニング(深層学習)のプログラムを生成できる統合開発環境「コンソールソフトウェア:Neural Network Console」の無償提供を本日より開始しました。


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

A Semiconductor That Can Beat the Heat | Berkeley Lab

A collective rattling effect in a type of crystalline semiconductor blocks most heat transfer while preserving high electrical conductivity.
more...
No comment yet.
Scooped by Shiwon Cho
Scoop.it!

Cheat Sheets for AI, Neural Networks, Machine Learning, Deep Learning & Big Data

Cheat Sheets for AI, Neural Networks, Machine Learning, Deep Learning & Big Data | EEDSP | Scoop.it
Over the past few months, I have been collecting AI cheat sheets. From time to time I share them with friends and colleagues and recently I have been getting asked a lot, so I decided to organize and…
more...
No comment yet.
Scooped by Shiwon Cho
Scoop.it!

Apple Machine Learning Journal

Apple has launched the ‘Machine Learning Journal’, a blog for Apple’s software engineers to document their research and innovations in the AI and machine learning space.
more...
No comment yet.
Scooped by Shiwon Cho
Scoop.it!

AI Co-Pilot: RNNs for Dynamic Facial Analysis | Parallel Forall

AI Co-Pilot: RNNs for Dynamic Facial Analysis | Parallel Forall | EEDSP | Scoop.it
Recurrent neural networks (RNNs) for joint estimation and dynamic facial analysis in videos enable automatic NVIDIA AI Co-Pilot for drivers.
more...
No comment yet.
Scooped by Shiwon Cho
Scoop.it!

Getting to know Neural Networks with Perceptron | Open Data Science

Editor's note: ODSC supports the self-education of data enthusiasts of all levels, building the access to information and the means to showcase their data
more...
No comment yet.