arXiv subjects

Claudia Linnhoff-Popien

Publications and source records attributed to Claudia Linnhoff-Popien.

At least 127 records · Page 7Linked to original sources

arXiv2022

VoronoiPatches: Evaluating A New Data Augmentation Method

Overfitting is a problem in Convolutional Neural Networks (CNN) that causes poor generalization of models on unseen data. To remediate this problem, many new and diverse data augmentation methods (DA) have been proposed to supplement or generate more training data, and thereby increase its quality. In this work, we propose a new data augmentation algorithm: VoronoiPatches (VP). We primarily utilize non-linear recombination of information within an image, fragmenting and occluding small information patches. Unlike other DA methods, VP uses small convex polygon-shaped patches in a random layout to transport information around within an image. Sudden transitions created between patches and the original image can, optionally, be smoothed. In our experiments, VP outperformed current DA methods regarding model variance and overfitting tendencies. We demonstrate data augmentation utilizing non-linear re-combination of information within images, and non-orthogonal shapes and structures improves CNN model robustness on unseen data.

cs.CV↗

arXiv2022

Empirical Analysis of Limits for Memory Distance in Recurrent Neural Networks

Common to all different kinds of recurrent neural networks (RNNs) is the intention to model relations between data points through time. When there is no immediate relationship between subsequent data points (like when the data points are generated at random, e.g.), we show that RNNs are still able to remember a few data points back into the sequence by memorizing them by heart using standard backpropagation. However, we also show that for classical RNNs, LSTM and GRU networks the distance of data points between recurrent calls that can be reproduced this way is highly limited (compared to even a loose connection between data points) and subject to various constraints imposed by the type and size of the RNN in question. This implies the existence of a hard limit (way below the information-theoretic one) for the distance between related data points within which RNNs are still able to recognize said relation.

cs.LG↗

arXiv2022

Capturing Dependencies within Machine Learning via a Formal Process Model

The development of Machine Learning (ML) models is more than just a special case of software development (SD): ML models acquire properties and fulfill requirements even without direct human interaction in a seemingly uncontrollable manner. Nonetheless, the underlying processes can be described in a formal way. We define a comprehensive SD process model for ML that encompasses most tasks and artifacts described in the literature in a consistent way. In addition to the production of the necessary artifacts, we also focus on generating and validating fitting descriptions in the form of specifications. We stress the importance of further evolving the ML model throughout its life-cycle even after initial training and testing. Thus, we provide various interaction points with standard SD processes in which ML often is an encapsulated task. Further, our SD process model allows to formulate ML as a (meta-) optimization problem. If automated rigorously, it can be used to realize self-adaptive autonomous systems. Finally, our SD process model features a description of time that allows to reason about the progress within ML development processes. This might lead to further applications of formal methods within the field of ML.

cs.SE↗

arXiv2022

Stochastic Market Games

Some of the most relevant future applications of multi-agent systems like autonomous driving or factories as a service display mixed-motive scenarios, where agents might have conflicting goals. In these settings agents are likely to learn undesirable outcomes in terms of cooperation under independent learning, such as overly greedy behavior. Motivated from real world societies, in this work we propose to utilize market forces to provide incentives for agents to become cooperative. As demonstrated in an iterated version of the Prisoner's Dilemma, the proposed market formulation can change the dynamics of the game to consistently learn cooperative policies. Further we evaluate our approach in spatially and temporally extended settings for varying numbers of agents. We empirically find that the presence of markets can improve both the overall result and agent individual returns via their trading activities.

cs.MA↗

arXiv2022

Towards Turing-Complete Quantum Computing Coming From Classical Assembler

Instead of producing quantum languages that are fit for current quantum computers, we build a language from standard classical assembler and augment it with quantum capabilities so that quantum algorithms become a subset of it. This paves the way for the development of hybrid algorithms directly from classical software, which is not feasible on today's hardware but might inspire future quantum programmers.

quant-ph↗

arXiv2022

Case-Based Inverse Reinforcement Learning Using Temporal Coherence

Providing expert trajectories in the context of Imitation Learning is often expensive and time-consuming. The goal must therefore be to create algorithms which require as little expert data as possible. In this paper we present an algorithm that imitates the higher-level strategy of the expert rather than just imitating the expert on action level, which we hypothesize requires less expert data and makes training more stable. As a prior, we assume that the higher-level strategy is to reach an unknown target state area, which we hypothesize is a valid prior for many domains in Reinforcement Learning. The target state area is unknown, but since the expert has demonstrated how to reach it, the agent tries to reach states similar to the expert. Building on the idea of Temporal Coherence, our algorithm trains a neural network to predict whether two states are similar, in the sense that they may occur close in time. During inference, the agent compares its current state with expert states from a Case Base for similarity. The results show that our approach can still learn a near-optimal policy in settings with very little expert data, where algorithms that try to imitate the expert at the action level can no longer do so.

cs.LG↗

arXiv2022

Algorithmic QUBO Formulations for k-SAT and Hamiltonian Cycles

Quadratic unconstrained binary optimization (QUBO) can be seen as a generic language for optimization problems. QUBOs attract particular attention since they can be solved with quantum hardware, like quantum annealers or quantum gate computers running QAOA. In this paper, we present two novel QUBO formulations for $k$-SAT and Hamiltonian Cycles that scale significantly better than existing approaches. For $k$-SAT we reduce the growth of the QUBO matrix from $O(k)$ to $O(log(k))$. For Hamiltonian Cycles the matrix no longer grows quadratically in the number of nodes, as currently, but linearly in the number of edges and logarithmically in the number of nodes. We present these two formulations not as mathematical expressions, as most QUBO formulations are, but as meta-algorithms that facilitate the design of more complex QUBO formulations and allow easy reuse in larger and more complex QUBO formulations.

cs.DS↗

arXiv2022

How to Approximate any Objective Function via Quadratic Unconstrained Binary Optimization

Quadratic unconstrained binary optimization (QUBO) has become the standard format for optimization using quantum computers, i.e., for both the quantum approximate optimization algorithm (QAOA) and quantum annealing (QA). We present a toolkit of methods to transform almost arbitrary problems to QUBO by (i) approximating them as a polynomial and then (ii) translating any polynomial to QUBO. We showcase the usage of our approaches on two example problems (ratio cut and logistic regression).

quant-ph↗

arXiv2022

Simple Quantum State Encodings for Hybrid Programming of Quantum Simulators

Especially sparse quantum states can be efficiently encoded with simple classical data structures. We show the admissibility of using a classical database to encode quantum states for a few practical examples and argue in favor of further optimizations for quantum simulation targeting simpler, only 'semi-quantum' circuits.

quant-ph↗

arXiv2021

Quantifying Multimodality in World Models

Model-based Deep Reinforcement Learning (RL) assumes the availability of a model of an environment's underlying transition dynamics. This model can be used to predict future effects of an agent's possible actions. When no such model is available, it is possible to learn an approximation of the real environment, e.g. by using generative neural networks, sometimes also called World Models. As most real-world environments are stochastic in nature and the transition dynamics are oftentimes multimodal, it is important to use a modelling technique that is able to reflect this multimodal uncertainty. In order to safely deploy such learning systems in the real world, especially in an industrial context, it is paramount to consider these uncertainties. In this work, we analyze existing and propose new metrics for the detection and quantification of multimodal uncertainty in RL based World Models. The correct modelling & detection of uncertain future states lays the foundation for handling critical situations in a safe way, which is a prerequisite for deploying RL systems in real-world settings.

cs.LG↗

arXiv2021

Acoustic Leak Detection in Water Networks

In this work, we present a general procedure for acoustic leak detection in water networks that satisfies multiple real-world constraints such as energy efficiency and ease of deployment. Based on recordings from seven contact microphones attached to the water supply network of a municipal suburb, we trained several shallow and deep anomaly detection models. Inspired by how human experts detect leaks using electronic sounding-sticks, we use these models to repeatedly listen for leaks over a predefined decision horizon. This way we avoid constant monitoring of the system. While we found the detection of leaks in close proximity to be a trivial task for almost all models, neural network based approaches achieve better results at the detection of distant leaks.

cs.LG↗

arXiv2020

SAT-MARL: Specification Aware Training in Multi-Agent Reinforcement Learning

A characteristic of reinforcement learning is the ability to develop unforeseen strategies when solving problems. While such strategies sometimes yield superior performance, they may also result in undesired or even dangerous behavior. In industrial scenarios, a system's behavior also needs to be predictable and lie within defined ranges. To enable the agents to learn (how) to align with a given specification, this paper proposes to explicitly transfer functional and non-functional requirements into shaped rewards. Experiments are carried out on the smart factory, a multi-agent environment modeling an industrial lot-size-one production facility, with up to eight agents and different multi-agent reinforcement learning algorithms. Results indicate that compliance with functional and non-functional constraints can be achieved by the proposed approach.

cs.LG↗

arXiv2020

Acoustic Anomaly Detection for Machine Sounds based on Image Transfer Learning

In industrial applications, the early detection of malfunctioning factory machinery is crucial. In this paper, we consider acoustic malfunction detection via transfer learning. Contrary to the majority of current approaches which are based on deep autoencoders, we propose to extract features using neural networks that were pretrained on the task of image classification. We then use these features to train a variety of anomaly detection models and show that this improves results compared to convolutional autoencoders in recordings of four different factory machines in noisy environments. Moreover, we find that features extracted from ResNet based networks yield better results than those from AlexNet and Squeezenet. In our setting, Gaussian Mixture Models and One-Class Support Vector Machines achieve the best anomaly detection performance.

eess.AS↗

arXiv2020

A Quantum Annealing Algorithm for Finding Pure Nash Equilibria in Graphical Games

We introduce Q-Nash, a quantum annealing algorithm for the NP-complete problem of Fnding pure Nash equilibria in graphical games. The algorithm consists of two phases. The first phase determines all combinations of best response strategies for each player using classical computation. The second phase finds pure Nash equilibria using a quantum annealing device by mapping the computed combinations to a quadratic unconstrained binary optimization formulation based on the Set Cover problem. We empirically evaluate Q-Nash on D-Wave's Quantum Annealer 2000Q using different graphical game topologies. The results with respect to solution quality and computing time are compared to a Brute Force algorithm and the Iterated Best Response heuristic.

cs.GT↗

arXiv2020

Cross Entropy Hyperparameter Optimization for Constrained Problem Hamiltonians Applied to QAOA

Hybrid quantum-classical algorithms such as the Quantum Approximate Optimization Algorithm (QAOA) are considered as one of the most encouraging approaches for taking advantage of near-term quantum computers in practical applications. Such algorithms are usually implemented in a variational form, combining a classical optimization method with a quantum machine to find good solutions to an optimization problem. The solution quality of QAOA depends to a high degree on the parameters chosen by the classical optimizer at each iteration. However, the solution landscape of those parameters is highly multi-dimensional and contains many low-quality local optima. In this study we apply a Cross-Entropy method to shape this landscape, which allows the classical optimizer to find better parameter more easily and hence results in an improved performance. We empirically demonstrate that this approach can reach a significant better solution quality for the Knapsack Problem.

quant-ph↗

arXiv2020

Surgical Mask Detection with Convolutional Neural Networks and Data Augmentations on Spectrograms

In many fields of research, labeled datasets are hard to acquire. This is where data augmentation promises to overcome the lack of training data in the context of neural network engineering and classification tasks. The idea here is to reduce model over-fitting to the feature distribution of a small under-descriptive training dataset. We try to evaluate such data augmentation techniques to gather insights in the performance boost they provide for several convolutional neural networks on mel-spectrogram representations of audio data. We show the impact of data augmentation on the binary classification task of surgical mask detection in samples of human voice (ComParE Challenge 2020). Also we consider four varying architectures to account for augmentation robustness. Results show that most of the baselines given by ComParE are outperformed.

eess.AS↗

arXiv2020

Content-based Recommendations for Radio Stations with Deep Learned Audio Fingerprints

The world of linear radio broadcasting is characterized by a wide variety of stations and played content. That is why finding stations playing the preferred content is a tough task for a potential listener, especially due to the overwhelming number of offered choices. Here, recommender systems usually step in but existing content-based approaches rely on metadata and thus are constrained by the available data quality. Other approaches leverage user behavior data and thus do not exploit any domain-specific knowledge and are furthermore disadvantageous regarding privacy concerns. Therefore, we propose a new pipeline for the generation of audio-based radio station fingerprints relying on audio stream crawling and a Deep Autoencoder. We show that the proposed fingerprints are especially useful for characterizing radio stations by their audio content and thus are an excellent representation for meaningful and reliable radio station recommendations. Furthermore, the proposed modules are part of the HRADIO Communication Platform, which enables hybrid radio features to radio stations. It is released with a flexible open source license and enables especially small- and medium-sized businesses, to provide customized and high quality radio services to potential listeners.

cs.HC↗

arXiv2020

Policy Entropy for Out-of-Distribution Classification

One critical prerequisite for the deployment of reinforcement learning systems in the real world is the ability to reliably detect situations on which the agent was not trained. Such situations could lead to potential safety risks when wrong predictions lead to the execution of harmful actions. In this work, we propose PEOC, a new policy entropy based out-of-distribution classifier that reliably detects unencountered states in deep reinforcement learning. It is based on using the entropy of an agent's policy as the classification score of a one-class classifier. We evaluate our approach using a procedural environment generator. Results show that PEOC is highly competitive against state-of-the-art one-class classification algorithms on the evaluated environments. Furthermore, we present a structured process for benchmarking out-of-distribution classification in reinforcement learning.

cs.LG↗