Content based image retrieval is a field in computer vision. The aim is to find the most similar images to a given input image, where the similarity refers to the sem
In the second article of our blog post series about TensorFlow Mobile we are working on quantization-aware model training with the TensorFlow Object Detection API. In the hands-on example we build and train a quantization-aware object detector for cars.
This is the second article of our blog post series about TensorFlow Mo
Learning is a process that can be observed across all living creatures – and also machines with the advent of sophisticated hardware and algorithms. This article introduces preference-based inverse reinforcement learning and explains how it can support a snake-like robot to learn to move forward efficiently.
Humans are constantly being taught and acquire knowledge: first by parents, later in school by teachers and at work by colleagues. In fact, learning is a process that
This first post tackles some of the theoretical background of on-device machine learning, including quantization and state-of-the-art model architectures for TensorFlow Lite.
The amount of mobile applications making use of some sort of machine learning is quickly increasing, just as the number of potential use cases in this area. Whenever
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-
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
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
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
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
We extend state-of-the-art sequence-to-sequence neural networks for summarization of long text across windows. By learning transitions, we are able to process arbitrarily long texts during inference.
This blog post describes my master thesis "Abstractive Summarization for Long Texts". We’ve extended existing state-of-the-art sequence-to-sequence (Seq2Seq) neural net
Everybody talks about AI and deep learning and everybody uses it, including you! But what exactly is deep learning and what are artificial neural networks? In this article I shine a light on some basic yet crucial concepts in an attempt to lift the veil.
Artificial intelligence or deep learning: Everybody talks about it and everybody uses it, including you! Of course you immediately have the evil terminator in mind wh
This article presents SeqPolicyNet, our Deep Learning approach to accessing information stored in an Elasticsearch instance given natural language questions.
tl;dr (spoiler alert): We’ve trained an advanced neural network to query Elasticsearch
This article unveils the connections between artificial intelligence, machine learning and deep learning based on a simple example. It suits as an introduction for newbies as well as a reference point for advanced readers looking for more complex content.
There has always been a gap between the capabilities of men and machine. While computers were able to perform complex multiplications or store large amounts of data,
In this blogposts on deep learning model exploration, translation, and deployment we expand on the previous article with two additional approaches for model deployment: TensorFlow Serving and Docker as well as a rather hobbyist approach in which we build a simple web application that serves our model.
This is the second part of a series of two blogposts on deep learning model exploration, translation, and deployment. Both involve many technologies like PyTorch, Ten
In the last years, artificial neural networks (ANN) have successfully been applied across a number of tasks. However, designing well performing ANNs requires expert knowledge and experience. Neuroevolution aims at solving this difficult and often time-consuming process by using evolutionary techniques.
In the last years, artificial neural networks (ANN) have successfully been applied across a number of tasks, such as image classification, speech recognition and natu