Federated Learning: Frameworks for Decentralized Private Training – Part 2

2020-10-16T12:31:12+00:00

This blogpost evaluates three different Federated Learning frameworks and the concepts they use to achieve a collaborative training. With Federated Learning, numerous previously unusable sensitive data sources now can be used for collaborative Machine Learning.

This blog post evaluates three different Federated Learning frameworks and

Federated Learning: Frameworks for Decentralized Private Training – Part 22020-10-16T12:31:12+00:00

Using Artificial Intelligence in Mobile Web Apps

2020-10-12T09:50:36+00:00

As the evaluation of a prototype shows, artificial intelligence is currently only of limited use in the context of a mobile web application. However, it is quite conceivable to already use smaller models for simple use cases, which produce consistently correct results with only a small amount of training data.

For my bachelor’s thesis, I evaluated the applicability of artificial intelligence within a mobile web application. Therefore, a prototype for classifying handwritten

Using Artificial Intelligence in Mobile Web Apps2020-10-12T09:50:36+00:00

Unsere Erfahrung mit Remote Teaching: Das KI Labor im Sommersemester 2020

2020-09-08T14:42:56+00:00

inovex betreut das Labor „Künstliche Intelligenz” für den Masterstudiengang Informatik an der Hochschule Karlsruhe. Im Sommersemester 2020 fand das AI Lab remote statt, mit Hilfe von Google Colaboratory – hier schildern wir unsere Erfahrung mit Remote Teaching.

Im Rahmen der Vertiefungsrichtung Maschinelles Lernen betreut inovex das Labor „Künstliche Intelligenz” für den Masterstudiengang Informatik an der Hochschule Karlsru

Unsere Erfahrung mit Remote Teaching: Das KI Labor im Sommersemester 20202020-09-08T14:42:56+00:00

Federated Learning: A Guide to Collaborative Training with Decentralized Sensitive Data – Part 1

2020-10-12T15:59:59+00:00

This blog post explains how Federated Learning works and what privacy techniques are necessary to ensure that sensitive data is protected.

Nowadays, access to high-quality real-world data has a major impact on the success of data-driven projects, as the quality of a Machine Learning solution strongly dep

Federated Learning: A Guide to Collaborative Training with Decentralized Sensitive Data – Part 12020-10-12T15:59:59+00:00

Dive into Snorkel: Weak-Supervision on German Texts

2020-08-03T16:20:46+00:00

How do we proceed if we have almost no labeled data for a machine learning model? One answer may be: combining all the knowledge we have in one framework to get to the best of each world. This blogpost investigates the trending data programming framework Snorkel for the task of detecting bad language on German texts.

How do we proceed if we have almost no labeled data for a machine learning model? One answer may be: combining all the knowledge we have (labeled data, distant superv

Dive into Snorkel: Weak-Supervision on German Texts2020-08-03T16:20:46+00:00

mint:pro 2020 Webinar für Schüler:innen: Was ist eigentlich KI?

2020-07-07T14:57:11+00:00

Die Ausbildung von Schüler:innen soll trotz Corona nicht auf der Strecke bleiben. Am 22.6. haben wir den – ursprünglich in unserem Hamburger Office geplanten – Techday zum Thema „Was ist Künstliche Intelligenz (KI)” im Rahmen des Begabtenförderungprogramms mint:pro der Initiative NAT als Webinar stattfinden lassen.

COVID-19 – dieses Jahr ist alles anders – und dennoch soll die Ausbildung von Schüler:innen nicht auf der Strecke bleiben. Am 22.6. haben wir den – ursprünglich in un

mint:pro 2020 Webinar für Schüler:innen: Was ist eigentlich KI?2020-07-07T14:57:11+00:00

Blockchain-Lösungen für den produktionstechnischen Mittelstand

2020-10-06T11:18:04+00:00

Die Digitalisierung findet Einzug in den deutschen produktionstechnischen Mittelstand. Bisherige Ansätze beschränken sich auf die Optimierungen firmeninterner Prozesse. Der nächste Schritt ist die Nutzung dieser Ansätze, um firmenübergreifende Geschäftsmodelle zu realisieren.

Hinweis: Der folgende Artikel ist zuerst im Onlinemagazin wt Werkstattstechnik, Band 111 (Nr.4), S.201-204, 2020 erschienen. Die Digitalisierung findet Einzug in den deu

Blockchain-Lösungen für den produktionstechnischen Mittelstand2020-10-06T11:18:04+00:00

End-to-End Image Captioning

2020-05-01T15:23:28+00:00

We had the unique opportunity to develop an image captioning system combining computer vision and NLP from a prototype model to a fully scalable data product with a team of five interdisciplinary students from the TUM Data Innovation Lab during a period of six months as part of an educational research experience.

tl;dr Data Science, Machine Learning Engineering, Software Engineering, and IT-Operations know-how is required to turn a prototypical machine-learning model into an end-

End-to-End Image Captioning2020-05-01T15:23:28+00:00

Software Defined Networks: Are AI Algorithms Replacing Shortest Path?

2020-03-30T08:00:12+00:00

For my master’s thesis I evaluated whether AI and metaheuristic routing algorithms implemented in Software Defined Networks can improve the overall performance of computer networks. Curious whether OSPF and BGP are getting shelved soon? Find out here!

For my master’s thesis I evaluated whether AI and metaheuristic routing algorithms implemented in Software Defined Networks can improve the overall performance of com

Software Defined Networks: Are AI Algorithms Replacing Shortest Path?2020-03-30T08:00:12+00:00

SocialVisTUM: Visualize and Label Clusters of Social Media Texts

2020-03-16T10:10:26+00:00

We developed SocialVisTUM, a new user-friendly visualization and labeling toolkit which enables users to get a quick and comprehensible visual overview of topics and topic relations for any English text corpus and can be accessed online. Read on for the details and an interactive demo!

Web sources such as social networks, internet forums, and user reviews, provide large amounts of unstructured text data. Due to the steady development of new platform

SocialVisTUM: Visualize and Label Clusters of Social Media Texts2020-03-16T10:10:26+00:00

mint:pro 2020: Schüler:innen entwickeln KI-Geschäftsideen

2020-03-18T11:35:32+00:00

Bereits im letzten Jahr hat Marisa Schüler:innen von mint:pro zu einem Exkurs zu PlanetAI nach Rostock begleitet. Für die kommenden sechs Monate heißt es erneut: Entwickle eine Idee für ein Startup im Bereich künstliche Intelligenz (KI) – dieses Mal mit inovex als festem Programmpartner.

Bereits im letzten Jahr hat Marisa einige Schüler:innen des Begabtenförderungsprogramms mint:pro der Initiative NAT zu einem Exkurs zu PlanetAI nach Rostock begleitet

mint:pro 2020: Schüler:innen entwickeln KI-Geschäftsideen2020-03-18T11:35:32+00:00

3D Deep Learning with TensorFlow 2

2020-03-09T17:36:48+00:00

In this blog post, we will first have a look at 3D deep learning with PointNet. Its creators provide a TensorFlow 1.x implementation of PointNet on Github, but since TensorFlow 2.0 was released in the meantime, we will transform it into an idiomatic TensorFlow 2 implementation in the second part of this post.

The world that we interact with each and every day is three-dimensional, but the majority of deep learning models process visual data as 2D images. However, there are

3D Deep Learning with TensorFlow 22020-03-09T17:36:48+00:00

Machine Learning on the Edge for Parking Guidance Systems

2020-01-07T15:42:43+00:00

Machine Learning on the Edge becomes more and more important for Smart Cities. We investigate how Deep Learning models can be optimized and deployed on edge devices for smart parking guidance systems.

This blog post investigates how deep learning models can be optimized and deployed on edge devices for parking guidance systems. I will present two different approach

Machine Learning on the Edge for Parking Guidance Systems2020-01-07T15:42:43+00:00

Transfer Learning for Text Classification with Siamese Networks

2020-03-19T10:02:10+00:00

In this blogpost, I want to present my master's thesis, which focused on transfer learning for text classification using Siamese Networks.

Text classification is a field in natural language processing (NLP), which assigns text to given classes. With applications in sentiment analysis, spam detection or i

Transfer Learning for Text Classification with Siamese Networks2020-03-19T10:02:10+00:00

Uncertainty Quantification in Deep Learning

2019-10-09T14:17:31+00:00

Teach your Deep Neural Network to be aware of its epistemic and aleatory uncertainty. Get a quantified confidence measure for your Deep Learning predictions.

Artificial Intelligence—and machine learning in particular—have come a long way since their early beginnings. The widespread availability and affordability of powerfu

Uncertainty Quantification in Deep Learning2019-10-09T14:17:31+00:00
Mehr Beiträge laden