Search Results for author:
Found 22 papers, 4 papers with code
Simulation-based Inference for Model Parameterization on Analog Neuromorphic Hardware
In contrast to other optimization methods such as genetic algorithms or stochastic searches, the SNPE algorithms belongs to the class of approximate Bayesian computing (ABC) methods and estimates the posterior distribution of the model parameters; access to the posterior allows classifying the confidence in parameter estimations and unveiling correlation between model parameters.
From Clean Room to Machine Room: Commissioning of the First-Generation BrainScaleS Wafer-Scale Neuromorphic System
The first-generation of BrainScaleS, also referred to as BrainScaleS-1, is a neuromorphic system for emulating large-scale networks of spiking neurons.
Understanding Concept Identification as Consistent Data Clustering Across Multiple Feature Spaces
To support the novel understanding of concept identification, we consider a simulated data set from a decision-making problem in the energy management domain and show that the identified clusters are more interpretable with respect to relevant feature subsets than clusters found by common clustering algorithms and are thus more suitable to support a decision maker.
Alleviating Search Bias in Bayesian Evolutionary Optimization with Many Heterogeneous Objectives
To this end, we develop a multi-objective Bayesian evolutionary optimization approach to HE-MOPs by exploiting the different data sets on the cheap and expensive objectives in HE-MOPs to alleviate the search bias caused by the heterogeneous evaluation costs for evaluating different objectives.
Concept Identification for Complex Engineering Datasets
In this work, an approach to define meaningful and consistent concepts in an existing engineering dataset is presented.
Recent Advances in Bayesian Optimization
Bayesian optimization has emerged at the forefront of expensive black-box optimization due to its data efficiency.
Stream-based Active Learning with Verification Latency in Non-stationary Environments
Furthermore, we propose a drift-dependent dynamic budget strategy, which uses a variable distribution of the labelling budget over time, after a detected drift.
A Scalable Approach to Modeling on Accelerated Neuromorphic Hardware
Neuromorphic systems open up opportunities to enlarge the explorative space for computational research.
Interaction-Aware Sensitivity Analysis for Aerodynamic Optimization Results using Information Theory
We thus demonstrate the power of novel information-theoretic approaches in identifying relevant parameters in optimization runs and highlight how these methods avoid the selection of redundant parameters, while detecting interactions that result in synergistic contributions of multiple parameters.
Transfer Learning Based Co-surrogate Assisted Evolutionary Bi-objective Optimization for Objectives with Non-uniform Evaluation Times
Most existing multiobjetive evolutionary algorithms (MOEAs) implicitly assume that each objective function can be evaluated within the same period of time.
Task-Sensitive Concept Drift Detector with Constraint Embedding
In the proposed framework, the actual method to detect a change in the statistics of incoming data samples can be chosen freely.
A Rigorous Information-Theoretic Definition of Redundancy and Relevancy in Feature Selection Based on (Partial) Information Decomposition
We argue that this lack is inherent to classical information theory which does not provide measures to decompose the information a set of variables provides about a target into unique, redundant, and synergistic contributions.
Estimating the electrical power output of industrial devices with end-to-end time-series classification in the presence of label noise
However, sensor failures result in mislabeled training data samples which are hard to detect and remove from the dataset.
PREPRINT: Comparison of deep learning and hand crafted features for mining simulation data
The output of such simulations, in particular the calculated flow fields, are usually very complex and hard to interpret for realistic three-dimensional real-world applications, especially if time-dependent simulations are investigated.
Preprint: Norm Loss: An efficient yet effective regularization method for deep neural networks
In this work we propose a weight soft-regularization method based on the Oblique manifold.
Real-World Anomaly Detection by using Digital Twin Systems and Weakly-Supervised Learning
The approaches make use of a Digital Twin to generate a training dataset which simulates the normal operation of the machinery, along with a small set of labeled anomalous measurement from the real machinery.
hxtorch: PyTorch for BrainScaleS-2 -- Perceptrons on Analog Neuromorphic Hardware
We present software facilitating the usage of the BrainScaleS-2 analog neuromorphic hardware system as an inference accelerator for artificial neural networks.
The Operating System of the Neuromorphic BrainScaleS-1 System
We present operation and development methodologies implemented for the BrainScaleS-1 neuromorphic architecture and walk through the individual components of BrainScaleS OS constituting the software stack for BrainScaleS-1 platform operation.
Exploring the fitness landscape of a realistic turbofan rotor blade optimization
The choices to be made in the setup of the optimization process strongly influence this mapping and thus are expected to have a profound influence on the achievable result.
Accelerated physical emulation of Bayesian inference in spiking neural networks
The massively parallel nature of biological information processing plays an important role for its superiority to human-engineered computing devices.
Pattern representation and recognition with accelerated analog neuromorphic systems
Despite being originally inspired by the central nervous system, artificial neural networks have diverged from their biological archetypes as they have been remodeled to fit particular tasks.
Neuromorphic Hardware In The Loop: Training a Deep Spiking Network on the BrainScaleS Wafer-Scale System
In this paper, we demonstrate how iterative training of a hardware-emulated network can compensate for anomalies induced by the analog substrate.
