
Christoffer LöfflerPontifical Catholic University of Valparaíso | PUCV · School of Computer Engineering
Christoffer Löffler
Doctor of Engineering
About
24
Publications
9,357
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
128
Citations
Introduction
I am an associate profesor at the school of informatics at PUCV and work on machine learning, active learning and with time series data.
Skills and Expertise
Additional affiliations
Education
January 2013 - December 2014
October 2009 - December 2012
Publications
Publications (24)
Learning from time series data is an essential component in the AI landscape given the ubiquitous time-dependent data in real-world applications. To motivate the necessity of learning from time series data, we first introduce different applications, data sources, and properties. These can be as diverse as irregular and (non-)continuous time series...
Modern machine and deep learning require large amounts of training data. Yet, even if the data itself is abundantly available, the fraction of annotated data may still be proportionally small or missing. Hence, learning with limited labeled data is an important research field. Two streams of research attack this problem from opposite directions [64...
Population-based metaheuristics can be seen as a set of agents that smartly explore the space of solutions of a given optimization problem. These agents are commonly governed by movement operators that decide how the exploration is driven. Although metaheuristics have successfully been used for more than 20 years, performing rapid and high-quality...
In recent years Deep Learning has revolutionized many fields in computer science such as Computer Vision (CV), Natural Language Processing (NLP), and Information Retrieval (IR). For example, modern DL is at the core of systems that process large amounts of complex data, such as images, video or text, and then retrieve information or even generate s...
Humans innately measure the distance between instances in an unlabeled dataset using an unknown similarity function. Distance metrics can only serve as a proxy for similarity in information retrieval of similar instances. Learning a good similarity function from human annotations improves the quality of retrievals. This work uses deep metric learni...
Humans innately measure distance between instances in an unlabeled dataset using an unknown similarity function. Distance metrics can only serve as proxy for similarity in information retrieval of similar instances. Learning a good similarity function from human annotations improves the quality of retrievals. This work uses deep metric learning to...
The correct interpretation and understanding of deep learning models is essential in many applications. Explanatory visual interpretation approaches for image and natural language processing allow domain experts to validate and understand almost any deep learning model. However, they fall short when generalizing to arbitrary time series data that i...
This work proposes metric learning for fast similarity-based scene retrieval of unstructured ensembles of trajectory data from large databases. We present a novel representation learning approach using Siamese Metric Learning that approximates a distance preserving low-dimensional representation and that learns to estimate reasonable solutions to t...
Active learning prioritizes the labeling of the most informative data samples. However, the performance of active learning heuristics depends on both the structure of the underlying model architecture and the data. We propose IALE, an imitation learning scheme that imitates the selection of the best-performing expert heuristic at each stage of the...
Despite the ongoing automation of modern production processes manual labor continues to be necessary due to its flexibility and ease of deployment. Automated processes assure quality and traceability, yet manual labor introduces gaps into the quality assurance process. This is not only undesirable but even intolerable in many cases.
Given the presence of deep neural networks (DNNs) in all kinds of applications, the question of optimized deployment is becoming increasingly important. One important step is the automated size reduction of the model footprint. Of all the methods emerging, post-training quantization is one of the simplest to apply. Without needing long processing o...
The ongoing automation of modern production processes requires novel human-computer interaction concepts that support employees in dealing with the unstoppable increase in time pressure, cognitive load, and the required fine-grained and process-specific knowledge. Augmented Reality (AR) systems support employees by guiding and teaching work process...
Active learning (AL) prioritizes the labeling of the most informative data samples. As the performance of well-known AL heuristics highly depends on the underlying model and data, recent heuristic-independent approaches that are based on reinforcement learning directly learn a policy that makes use of the labeling history to select the next sample....
Visual Odometry (VO) accumulates a positional drift in long-term robot navigation tasks. Although Convolutional Neural Networks (CNNs) improve VO in various aspects, VO still suffers from moving obstacles, discontinuous observation of features, and poor textures or visual information. While recent approaches estimate a 6DoF pose either directly fro...
Visual Odometry (VO) accumulates a positional drift in long-term robot navigation tasks. Although Convolutional Neural Networks (CNNs) improve VO in various aspects, VO still suffers from moving obstacles, discontinuous observation of features, and poor textures or visual information. While recent approaches estimate a 6DoF pose either directly fro...
Outside-in camera-based localization systems determine the position of mobile objects (with markers attached to them) by observing a tracking area with multiple camera anchors. Up to now the identification of the objects in the camera images only works for close objects (with passive 3- dimensional marker constellations) or when tracking gaps or a...
Real-time tracking allows to trace goods and enables the optimization of logistics processes in many application areas. Camera-based inside-out tracking that uses an infrastructure of fixed and known markers is costly as the markers need to be installed and maintained in the environment. Instead, systems that use natural markers suffer from changes...
A method (100) to determine a present position (122) of an object (600). The method (100) comprises using (102) an optical positioning system (104) to determine a first preliminary position (112) and using (106) a radio-based positioning system (108) to determine a second preliminary position (114), determining (110) a supposed position (116) on th...
Event-Based Systems (EBS) can efficiently analyze large streams of sensor data in near-realtime. But they struggle with noise or incompleteness that is seen in the unprecedented amount of data generated by the Internet of Things.
We present a generic approach that deals with uncertain data in the middleware layer of distributed event-based systems...
The DEBS 2014 Grand Challenge targets the monitoring and prediction of energy loads of smart plugs installed in private households. This paper presents details of our middleware solution and efficient median calculation, shows how we address data quality issues, and provides insights into our enhanced prediction based on hidden Markov models.
The e...
With the global growth of the market for smartphones new business ideas and applications are developed continuously. These often utilize the resources of a mobile device to a considerable extent and reach the limits of these. In this work we focus on the simulation of an on-demand music service on a modern smartphone. Our simulation model includes...
Event-based systems (EBS) are widely used to efficiently process massively parallel data streams. In distributed event processing the allocation of event detectors to machines is crucial for both the latency and efficiency, and a naive allocation may even cause a system failure. But since data streams, network traffic, and event loads cannot be pre...