Panggi Libersa Jasri Akadol

2,972 Flips | 1 Magazine | 2 Likes | 14 Following | 249 Followers | @panggi | I love Computer and Natural Science. I question everything, i care less about labels and more about truth. http://www.panggi.com

Open source "Gandiva" project wants to unblock analytics

Analytics involves repetitive calculations over huge volumes of data. GPUs and even CPUs can make that work go faster, if only the code and execution …

Big Data

Stanford Researchers Trained a Neural Network to Make These Memes

The model was trained on hundreds of memes in the “advice animal” style of text and image then tasked with producing its own captions.<p>Artificial intelligence can do some remarkable things, from driving cars to improving breast cancer diagnosis. And now it can make memes.<p>Abel Peirson and Meltem …

Machine Learning

Wolfram Research goes for Software 2.0, releases neural net repository

Wolfram, having been into AI before it was cool, now gets a piece of the deep learning hype, in its sui generis way. Where does it stand compared to …

Deep Learning

Use pre-trained models with Apache MXNet | Amazon Web Services

In this blog post, I’ll show you how to use multiple pre-trained models with Apache MXNet. Why would you want to try multiple models? Why not just …

Colab: An easy way to learn and use TensorFlow

Colaboratory is a hosted Jupyter notebook environment that is free to use and requires no setup. You may have already seen it in Machine Learning …

Here's why thousands of AI researchers will boycott a science journal

Popular science journal <i>Nature</i> recently announced the creation of a new closed-access section of its publication dedicated to machine learning, to be launched in January 2019. The AI community’s reaction was, predictably, less than positive.<p>Secrets don’t help science. The field of machine learning …

Google-led Kubeflow, machine learning for Kubernetes, begins to take shape

Ever since Google created Kubernetes as an open source container orchestration tool, it has seen it blossom in ways it might never have imagined. As the project gains in popularity, we are seeing many adjunct programs develop. Today, Google announced the release of version 0.1 of the Kubeflow open …

Nvidia is using deep learning to reconstruct missing parts of photos (and it's very accurate)

Retouching images is often synonymous with Adobe Photoshop but Nvidia holds the hardware required for advanced manipulation techniques. Using an …

Compositional Attention Networks for Machine Reasoning

<b>How should we design a neural network that doesn’t just learn, but also thinks?</b> We are undeniably in the midst of an AI golden age, with machines …

How to (quickly) build a deep learning image dataset

An example of a Pokedex (thank you to Game Trader USA for the Pokedex template!)When I was a kid, I was a <i>huge</i> Pokemon nerd. I collected the trading …

ANN Visualizer

A great visualization python library used to work with Keras. It uses python's graphviz library to create a presentable graph of the neural network …

Comparing Deep Learning Frameworks: A Rosetta Stone Approach

<i>This post is authored by Ilia Karmanov, Mathew Salvaris, Miguel Fierro, Danielle Dean, all Data Scientists at Microsoft.</i><p>With this blog post, we are …

Day 5: Building a Recommendation System Using Machine Learning (ML) and Artificial Intelligence (AI)

This article is a part of my year-long quest to master 12 incredibly hard skills, one a month.<p>Learning anything new? Invest.<p>The last update I wrote …

Machine Learning

How to create a poet / writer using Deep Learning (Text Generation using Python)?

We use cookies on Analytics Vidhya websites to deliver our services, analyze web traffic, and improve your experience on the site. By using Analytics …

Deep Learning

What’s New in Deep Learning Research: Understanding DeepMind’s IMPALA

Deep reinforcement learning has rapidly become one of the hottest research areas in the deep learning ecosystem. The fascination with reinforcement …

Getting Value from Machine Learning Isn’t About Fancier Algorithms — It’s About Making It Easier to Use

Machine learning can drive tangible business value for a wide range of industries — but only if it is actually put to use. Despite the many machine learning discoveries being made by academics, new research papers showing what is possible, and an increasing amount of data available, companies are …

You can take Google's Machine Learning Crash Course for free now

Google’s new ‘Machine Learning Crash Course’ is now available and it’s free for everyone. If robots are coming for your job this class will prepare you for your next one.<p>This same course has been taken by more than 18,000 Google engineers, and this is the first time it’s been made available to the …

Deep Learning from first principles in Python, R and Octave – Part 3

(This article was first published on <b> R – Giga thoughts …</b>, and kindly contributed to R-bloggers)<i>“Once upon a time, I, Chuang Tzu, dreamt I was a</i> …

Learning representations by back-propagating errors

Learning representations by back-propagating errors Rumelhart et al., <i>Nature, 1986</i>It’s another selection from Martonosi’s 2015 Princeton course on …

A Beginner's Guide to Deep Reinforcement Learning - Deeplearning4j: Open-source, Distributed Deep Learning for the JVM

A Beginner’s Guide to Deep Reinforcement Learning<p>Contents<p>Reinforcement Learning Definitions<br>• Domain Selection for Reinforcement Learning<br>• State-Action …

The 8 Neural Network Architectures Machine Learning Researchers Need to Learn

In this blog post, I want to share the 8 neural network architectures from the course that I believe any machine learning researchers should be …

Logo detection using Apache MXNet

<i>Image recognition and machine learning for mar tech and ad tech.</i>Digital marketing is the marketing of products, services, and offerings on digital …

A scalable Keras + deep learning REST API

In today’s blog post we are going to create a deep learning REST API that wraps a Keras model in an efficient, scalable manner.Our Keras + deep …

Twitter's Latest Photo Update Is So Brilliant You Won't Even Notice It

Twitter’s latest behind-the-scenes photo upgrade is significant and quite brilliant, but many users won’t even notice it.<p>Posting on a recent Twitter Engineering blog, researchers Lucas Theis and Zehan Wang detail how neural networks are now being used to dramatically improve the way images are …

IPhone 8

Build a social media dashboard using machine learning and BI services | Amazon Web Services

In this blog post we’ll show you how you can use Amazon Translate, Amazon Comprehend, Amazon Kinesis, Amazon Athena, and Amazon QuickSight to build a …

Amazon SageMaker BlazingText: Parallelizing Word2Vec on Multiple CPUs or GPUs | Amazon Web Services

Today we’re launching Amazon SageMaker BlazingText as the latest built-in algorithm for Amazon SageMaker. BlazingText is an unsupervised learning …

Data May Be the New Oil, but Having Lots of It May Not Make You Rich

AI is coming. That is what we heard throughout 2017 and will likely continue to hear throughout this year. For established businesses that are not Google or Facebook, a natural question to ask is: What have we got that is going to allow us to survive this transition?<p>In our experience, when business …

57 Summaries of Machine Learning and NLP Research

Staying on top of recent work is an important part of being a good researcher, but this can be quite difficult. Thousands of new papers are published …

An Intuitive Introduction to Generative Adversarial Networks

<i>This article was jointly written by Keshav Dhandhania and Arash Delijani, bios below.</i>In this article, I’ll talk about <b>Generative Adversarial Networks</b>, …

Google’s self-training AI turns coders into machine-learning masters - MIT Technology Review

Google just made it a lot easier to build your very own custom AI system.<p>A new service, called Cloud AutoML, uses several machine-learning tricks to …

Machine Learning