Generative Adversarial Networks explained

2018-06-14T10:41:41+00:00

Recent improvements on the architecture and the training of Generative Adversarial Networks have rendered them applicable on a greater variety of problems, e.g sequential or discrete data. In this blog article we take a closer look on the general theoretical GAN architecture and its variations.

Neural networks are one of the technologies that have the potential to change our lives forever. Besides lots of applications and machines in the industry they have d

Generative Adversarial Networks explained 2018-06-14T10:41:41+00:00

Text Spotting using semi-supervised Generative Adversarial Networks

2018-05-26T14:14:03+00:00

We built a text spotting (OCR) pipeline that out-performed Google Cloud Vision using semi-supervised Generative Adversarial Networks.

Despite all advances in machine learning due to the advent of deep learning, the latter has one major shortcoming: It requires a lot of data during the learning proce

Text Spotting using semi-supervised Generative Adversarial Networks 2018-05-26T14:14:03+00:00

TensorFlow Mobile: Training and Deploying a Neural Network

2018-05-08T11:16:57+00:00

In this blog series we explain how you can train and deploy a convolutional neural network for image classification to a mobile app using TensorFlow Mobile.

Smart Assistants, fancy image filters in Snapchat and apps like Prisma all have one thing in common—they are powered by Machine Learning. The use of Machine Learning

TensorFlow Mobile: Training and Deploying a Neural Network 2018-05-08T11:16:57+00:00

Managing isolated Environments with PySpark

2018-04-10T13:30:43+00:00

In this article we present a simple solution for managing Isolated Environments with PySpark that we have been using in production for more than a year.

With the sustained success of the Spark data processing platform even data scientists with a strong focus on the Python ecosystem can no longer ignore it. Fortunately

Managing isolated Environments with PySpark 2018-04-10T13:30:43+00:00

Application of Differential Privacy and Randomized Response in Big Data

2018-03-01T09:15:11+00:00

In this blog, I’ll explain some of the basic concepts of differential privacy and talk about how I’ve used it in my Bachelor’s Thesis.

Differential Privacy is a topic of growing interest in the world of Big Data. It is currently being deployed by tech giants like Google and Apple to gain knowledge ab

Application of Differential Privacy and Randomized Response in Big Data 2018-03-01T09:15:11+00:00

Writing a Hive UDF for lookups

2018-02-07T14:42:53+00:00

Let's use a Hive UDF to perform lookups against resources residing in the Hadoop file system (HDFS) which allows non-equi joins.

In today’s blog I am going to take a look at a fairly mundane and unspectacular use of a Hive UDF (user-defined function), that of performing lookups against re

Writing a Hive UDF for lookups 2018-02-07T14:42:53+00:00

Data Science in Production: Packaging, Versioning and Continuous Integration

2018-02-07T14:53:36+00:00

Here's what changes when your data science project grows from a proof of concept. How do you deploy your model, how can updates be rolled out, ...?

A common pattern in most data science projects I participated in is that it’s all fun and games until someone wants to put it into production. From that point in time

Data Science in Production: Packaging, Versioning and Continuous Integration 2018-02-07T14:53:36+00:00

Network Anomaly Detection: Online vs. Offline Machine Learning

2018-02-07T14:54:11+00:00

In this part of our network anomaly detection blogpost series we want to compare two basically different styles of learning.

In this part of our network anomaly detection series we want to compare two basically different styles of learning. The very first post introduced the simple k-means 

Network Anomaly Detection: Online vs. Offline Machine Learning 2018-02-07T14:54:11+00:00

Sport-Tracking mit Elasticsearch [Meetup]

2018-02-07T14:54:40+00:00

In diesem Mittschnitt unseres Meetups zeigt Tracking Fan Wolfgang, wie er die Daten seiner Garmin Watch selbst mit Elasticsearch ausgewertet hat.

In diesem Mittschnitt unseres Meetups in Karlsruhe zeigt Wolfgang, ein begeisterter Triathlet und Tracking Fan, wie er die Daten seiner Garmin Watch selbst mit Elasti

Sport-Tracking mit Elasticsearch [Meetup] 2018-02-07T14:54:40+00:00

Powering a Data Hub at Otto Group BI with Schedoscope

2017-11-27T15:30:20+00:00

In order to build data services or advanced machine learning models, organizations must integrate large amounts of information from diverse sources.

In order to build data services or advanced machine learning models, organizations must integrate large amounts of information from diverse sources. As a central plac

Powering a Data Hub at Otto Group BI with Schedoscope 2017-11-27T15:30:20+00:00

Causal Inference and Propensity Score Methods

2017-11-27T15:30:21+00:00

In supervised learning, correlation is crucial to predict the target variable with the help of the feature variables. But what good is causation?

In the field of machine learning and particularly in supervised learning, correlation is crucial to predict the target variable with the help of the feature variables

Causal Inference and Propensity Score Methods 2017-11-27T15:30:21+00:00
Mehr Beiträge laden