EEDSP
20.5K views | +0 today
Follow
 
Scooped by Shiwon Cho
onto EEDSP
Scoop.it!

Enterprise-ready Tool Support for Apache Camel | Javalobby

Enterprise-ready Tool Support for Apache Camel | Javalobby | EEDSP | Scoop.it
Apache Camel is my favorite integration framework on the Java
platform due to great DSLs, a huge community, and so many different
components. Camel is used...
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!

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!

Jupyter + Tensorflow + Nvidia GPU + Docker + Google Compute Engine

Jupyter + Tensorflow + Nvidia GPU + Docker + Google Compute Engine | EEDSP | Scoop.it
TL;DR: Save time and headaches by following this recipe for working with Tensorflow, Jupyter, Docker, and Nvidia GPUs on Google Cloud. Motivation: Businesses like fast, data-driven insights, and they…
more...
No comment yet.
Scooped by Shiwon Cho
Scoop.it!

NVIDIA Working on Multi-Chip-Module GPUs | eTeknix

NVIDIA Working on Multi-Chip-Module GPUs | eTeknix | EEDSP | Scoop.it
Moore’s Law, though being pushed to the limit, is restricting processor development. New GPU architecture, for example, will rely on a 7nm process. Can wafers get much smaller than that and remain competitive? NVIDIA, though, thinks it has an alternative: Multi-Chip-Module (MCM ) GPUs. Multi-Chip-Module GPUs NVIDIA – with Arizona State University, University of Texas, …
more...
No comment yet.
Scooped by Shiwon Cho
Scoop.it!

LUIS: Language Understanding Intelligent Service

Language Understanding Intelligent Service (LUIS) offers a fast and effective way of adding language understanding to applications.
With LUIS, you can use pre-existing, world-class, pre-built models from Bing and Cortana whenever they suit your purposes -- and when you need specialized models,
LUIS guides you through the process of quickly building them.
more...
No comment yet.
Scooped by Shiwon Cho
Scoop.it!

NVIDIA TensorRT

NVIDIA TensorRT | EEDSP | Scoop.it

TensorRT 2 Released


TensorRT 2 is now available as a free download to the members of the NVIDIA Developer Program. Deliver up to 45x faster inference under 7 ms real-time latency with INT8 precision Integrate novel user defined layers as plugins using Custom Layer API Deploy sequence based models for image captioning, language translation and other applications using LSTM and GRU Recurrent Neural Networks (RNN) layers

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

Google’s Tensor2Tensor makes it easier to conduct deep learning experiments

Google’s Tensor2Tensor makes it easier to conduct deep learning experiments | EEDSP | Scoop.it
Google's brain team is open sourcing Tensor2Tensor, a new deep learning library designed to help researchers replicate results from recent papers in the field..
more...
No comment yet.
Scooped by Shiwon Cho
Scoop.it!

Google releases new TensorFlow Object Detection API

Google releases new TensorFlow Object Detection API | EEDSP | Scoop.it
Google is releasing a new TensorFlow object detection API to make it easier for developers and researchers to identify objects within images. Google is trying..
more...
No comment yet.
Scooped by Shiwon Cho
Scoop.it!

DeepMind Research – Kinetics | DeepMind

Kinetics is a large-scale, high-quality dataset of YouTube video URLs which include a diverse range of human focused actions. Our aim in releasing the Kinetics dataset is to help the machine learning community to advance models for video understanding.
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.
Scooped by Shiwon Cho
Scoop.it!

Building Your Own Neural Machine Translation System in TensorFlow

Building Your Own Neural Machine Translation System in TensorFlow | EEDSP | Scoop.it

Posted by Thang Luong, Research Scientist, and Eugene Brevdo, Staff Software Engineer, Google Brain Team Machine translation – 


Machine translation – the task of automatically translating between languages – is one of the most active research areas in the machine learning community. Among the many approaches to machine translation, sequence-to-sequence ("seq2seq") models [1, 2] have recently enjoyed great success and have become the de facto standard in most commercial translation systems, such as Google Translate, thanks to its ability to use deep neural networks to capture sentence meanings. However, while there is an abundance of material on seq2seq models such as OpenNMT or tf-seq2seq, there is a lack of material that teaches people both the knowledge and the skills to easily build high-quality translation systems.

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

Design patterns for microservices

Design patterns for microservices | EEDSP | Scoop.it
The AzureCAT patterns & practices team has published nine new design patterns on the Azure Architecture Center. These nine patterns are particularly useful when designing and implementing…
more...
No comment yet.
Scooped by Shiwon Cho
Scoop.it!

Deep Learning and GPU Acceleration in Hadoop 3.0 - Hortonworks

Deep Learning and GPU Acceleration in Hadoop 3.0 - Hortonworks | EEDSP | Scoop.it

Recently Raj Verma (President & COO of Hortonworks) spoke to Jim McHugh from Nvidia at the DataWorks Summit keynote in San Jose. Jim began by by talking about how parallel processing that is used in gaming is also essential to Deep Learning

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

Deep learning on Apache Spark and Apache Hadoop with Deeplearning4j - Cloudera Engineering Blog

Deep learning on Apache Spark and Apache Hadoop with Deeplearning4j - Cloudera Engineering Blog | EEDSP | Scoop.it
In late 2016, Ben Lorica of O’Reilly Media declared that “2017 will be the year the data science and big data community engage with AI technologies.” Deep learning on GPUs has pervaded universities and research organizations prior to 2017, but distributed deep learning on CPUs is now beginning to gain widespread adoption in a diverse set of companies and domains. While GPUs provide top-of-the-line performance in numerical computing, CPUs are also becoming more efficient and much of today’s existing hardware already has CPU computing power available in bulk. Read More
more...
No comment yet.
Scooped by Shiwon Cho
Scoop.it!

ParlAI

ParlAI | EEDSP | Scoop.it
ParlAI (pronounced “par-lay”) is a framework for dialog AI research, implemented in Python.
more...
No comment yet.
Scooped by Shiwon Cho
Scoop.it!

Big Data with Golang Instead of MapReduce

This is one of those software engineering ideas that I would normally warn you about. So many people use MapReduce that it seems foolhardy to use something else. But in this case, it turned out well. The project was a success, and we were able to accomplish our goals more quickly and with fewer resources than it would have taken with a MapReduce cluster. Background I work on 3d Warehouse for Trimble SketchUp (formerly Google). One of our focuses over the last year has been analytics - both for our customers and for our own internal use. Most business intelligence providers are expensive - anywhere from 100-500K per year. Even with that price point, it's still cheaper than engineering time, so that was originally the path we took.
more...
No comment yet.