EEDSP
21.2K views | +1 today
Follow
 
Scooped by Shiwon Cho
onto EEDSP
Scoop.it!

Using R — Packaging a C library in 15 minutes

Yes, this post condenses 50+ hours of learning into a 15 minute tutorial.  Read ‘em and weep.  (That is, you read while I weep.) OK.  For the last week I’ve been learning how to call C code as documented in … Continue reading →...
more...
No comment yet.
EEDSP
Digital Signal Processing, Data Analytics, Big Data, HPC, Deep Learning, GPGPU, Distributed and Parallel Computing, Natural Language Processing
Curated by Shiwon Cho
Your new post is loading...
Your new post is loading...
Scooped by Shiwon Cho
Scoop.it!

MaD TwinNet - ARG::TUT

MaD TwinNet - ARG::TUT | EEDSP | Scoop.it

This page is an on-line demo of our recent research results on monaural musical sound source separation. Full presentation of results and method is in our paper entitled: "MaD TwinNet: Masker-Denoiser Architecture with Twin Networks for Monaural Sound Source Separation" and submitted to IEEE IJCNN/WCCI 2018.

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

Twitter Sentiment Analysis using combined LSTM-CNN Models – B-sides

Twitter Sentiment Analysis using combined LSTM-CNN Models – B-sides | EEDSP | Scoop.it
Twitter Sentiment Analysis using combined LSTM-CNN Models
more...
No comment yet.
Scooped by Shiwon Cho
Scoop.it!

Announcing Tensor Comprehensions –

Announcing Tensor Comprehensions – | EEDSP | Scoop.it
Today, Facebook AI Research (FAIR) is announcing the release of Tensor Comprehensions, a C++ library and mathematical language that helps bridge the gap between researchers, who communicate in terms of mathematical operations, and engineers focusing on the practical needs of running large-scale models on various hardware backends. The main differentiating feature of Tensor Comprehensions is…
more...
No comment yet.
Scooped by Shiwon Cho
Scoop.it!

Weak Supervision: The New Programming Paradigm for Machine Learning

Weak Supervision: The New Programming Paradigm for Machine Learning | EEDSP | Scoop.it
Getting labeled training data has become the key development bottleneck in supervised machine learning. We provide a broad, high-level overview of recent weak supervision approaches, where noisier or higher-level supervision is used as a more expedient and flexible way to get supervision signal, in particular from subject matter experts (SMEs). We provide a simple, broad definition of weak supervision as being comprised of one or more noisy conditional distributions over unlabeled data, and focus on the key technical challenge of unifying and modeling these sources.
more...
No comment yet.
Scooped by Shiwon Cho
Scoop.it!

Machine Learning - The Journal of Physical Chemistry Letters (ACS Publications)

Machine Learning - The Journal of Physical Chemistry Letters (ACS Publications) | EEDSP | Scoop.it

The recent complete rout of top Go players by a deep learning neural network self-learned by AlphaGo has taken the world by storm. The neural network is one example of a larger class of machine learning algorithms and corresponding conceptual models that have have penetrated many fields, including our own of physical chemistry.

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

OryxProject/oryx: Oryx 2: Lambda architecture on Apache Spark, Apache Kafka for real-time large scale machine learning

OryxProject/oryx: Oryx 2: Lambda architecture on Apache Spark, Apache Kafka for real-time large scale machine learning | EEDSP | Scoop.it
oryx - Oryx 2: Lambda architecture on Apache Spark, Apache Kafka for real-time large scale machine learning
more...
No comment yet.
Scooped by Shiwon Cho
Scoop.it!

Winter Olympics 2018: Inside the Opening Ceremonies Drone Show

Winter Olympics 2018: Inside the Opening Ceremonies Drone Show | EEDSP | Scoop.it
The Pyeongchang opening ceremonies included a performance by 1,218 drones working in concert—a new world record.
more...
No comment yet.
Scooped by Shiwon Cho
Scoop.it!

China is rapidly closing the US’s lead in AI research

China is rapidly closing the US’s lead in AI research | EEDSP | Scoop.it

Every year, hundreds of researchers gather at the annual conference of the Association for the Advancement of Artificial Intelligence (AAAI) to hear presentations on the latest developments in AI. Increasingly, that means learning about the work of Chinese researchers. According to a study (paywall) published recently by economists at the University of Toronto, 23% of the authors of papers presented at the 2017 AAAI Conference on Artificial Intelligence were Chinese, compared to just 10% in 2012. At the same time, the share of US authors fell from 41% to 34%. The economists see this change as indicative of China’s rise to prominence in AI, and a harbinger of a future battle for AI supremacy between China and the US.

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

Why are GPUs necessary for training Deep Learning models?

Why are GPUs necessary for training Deep Learning models? | EEDSP | Scoop.it
This article explains the difference in CPUs & GPUs to help you understand the application of GPUs in training deep learning models. Brief history of GPUs.
more...
No comment yet.
Scooped by Shiwon Cho
Scoop.it!

Accelerated Spark on GPU-enabled clusters in Azure

Accelerated Spark on GPU-enabled clusters in Azure | EEDSP | Scoop.it
AZTK lets you to provision on-demand GPU enabled Spark clusters on top of Azure Batch's infrastructure, helping you take your high-performance GPU code and distribute it across your Spark cluster.
more...
No comment yet.
Scooped by Shiwon Cho
Scoop.it!

Deep Learning: A Critical Appraisal (2018)

Deep Learning: A Critical Appraisal, Gary Marcus, 2018. [Link] https://arxiv.org/abs/1801.00631
more...
No comment yet.
Scooped by Shiwon Cho
Scoop.it!

How to solve 90% of NLP problems: a step-by-step guide

Whether you are an established company or working to launch a new service, you can always leverage text data to validate, improve, and expand the functionalities of your product. The science of…
more...
No comment yet.
Scooped by Shiwon Cho
Scoop.it!

facebookresearch/Detectron

facebookresearch/Detectron | EEDSP | Scoop.it
Detectron - FAIR's research platform for object detection research, implementing popular algorithms like Mask R-CNN and RetinaNet.
more...
No comment yet.
Scooped by Shiwon Cho
Scoop.it!

13 Deep Learning Frameworks for Natural Language Processing in Python

In this paper, we discuss the most popular neural network frameworks and libraries that can be utilized for natural language processing (NLP) in the Python programming language.

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

Machine Learning Top 10 Open Source Projects (v.Feb 2018)

For the past month, we ranked nearly 250 Machine Learning Open Source Projects to pick the Top 10.
more...
No comment yet.
Scooped by Shiwon Cho
Scoop.it!

Deep Learning for Recommender Systems –

Finding a car that fits your preferences can be a very time-consuming task and may drive you crazy. On the other hand, with approximately 1.5 million cars on our platform, vehicle descriptions that are constantly changing and users that are still exploring may also drive us as the solution provider crazy. Under these circumstances, matching cars with users’ preferences is challenging and by the time you’ve found a match, your perfect car might be gone.

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

How I Shipped a Neural Network on iOS with CoreML, PyTorch, and React Native - Stefano J. Attardi

How I Shipped a Neural Network on iOS with CoreML, PyTorch, and React Native - Stefano J. Attardi | EEDSP | Scoop.it

PyTorch and CoreML on iOS with React Native

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

Meet Nicholas Mahon, Brooklyn Puppeteer Behind the Olympics Opening Ceremony

Meet Nicholas Mahon, Brooklyn Puppeteer Behind the Olympics Opening Ceremony | EEDSP | Scoop.it
The first five minutes of the internationally televised event required months of careful planning, design, and production by one puppeteer.
more...
No comment yet.
Scooped by Shiwon Cho
Scoop.it!

Introducing Model Server for Apache MXNet | AWS Machine Learning Blog

Introducing Model Server for Apache MXNet | AWS Machine Learning Blog | EEDSP | Scoop.it
Earlier this week, AWS announced the availability of Model Server for Apache MXNet, an open source component built on top of Apache MXNet for serving deep learning models. Apache MXNet is a fast and scalable training and inference framework with an easy-to-use, concise API for machine learning. With Model Server for Apache MXNet, engineers are […]
more...
No comment yet.
Scooped by Shiwon Cho
Scoop.it!

Docker for Windows Desktop... Now With Kubernetes! - Docker Blog

Docker for Windows Desktop... Now With Kubernetes! - Docker Blog | EEDSP | Scoop.it

Docker for Windows with beta support for using Kubernetes as your orchestrator

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

Progress in AI seems like it’s accelerating, but here’s why it could be plateauing

Progress in AI seems like it’s accelerating, but here’s why it could be plateauing | EEDSP | Scoop.it
Just about every AI advance you’ve heard of depends on a breakthrough that’s three decades old. Keeping up the pace of progress will require confronting AI’s serious limitations.
more...
No comment yet.
Scooped by Shiwon Cho
Scoop.it!

Optimization over Explanation – Berkman Klein Center Collection – Medium

Making AI more fair and ethical by demanding explanations for its outcomes is often the wrong tool for the job. Instead, we should be regulating what AI systems are optimized for.
more...
No comment yet.
Scooped by Shiwon Cho
Scoop.it!

Building a Worker Pool in Golang – uniplacesgeeks

Recently we created a service that handles all events between Salesforce and our Core (Uniplaces main API). Every time there’s an event on the platform that needs to be represented in Salesforce…
more...
No comment yet.
Scooped by Shiwon Cho
Scoop.it!

Benchmarking Tensorflow Performance on Next Generation GPUs

As machine learning (ML) researchers and practitioners continue to explore the bounds of deep learning, the need for powerful GPUs to both train and run these models grows ever stronger. New models…
more...
No comment yet.