Search Results for author:
Found 40 papers, 12 papers with code
Guided-SPSA: Simultaneous Perturbation Stochastic Approximation assisted by the Parameter Shift Rule
The computational complexity, in terms of the number of circuit evaluations required for gradient estimation by the parameter-shift rule, scales linearly with the number of parameters in VQCs.
Warm-Start Variational Quantum Policy Iteration
This objective can be achieved using policy iteration, which requires to solve a typically large linear system of equations.
Comprehensive Library of Variational LSE Solvers
Linear systems of equations can be found in various mathematical domains, as well as in the field of machine learning.
Qiskit-Torch-Module: Fast Prototyping of Quantum Neural Networks
Quantum computer simulation software is an integral tool for the research efforts in the quantum computing community.
Few-Shot Learning with Uncertainty-based Quadruplet Selection for Interference Classification in GNSS Data
Jamming devices pose a significant threat by disrupting signals from the global navigation satellite system (GNSS), compromising the robustness of accurate positioning.
Velocity-Based Channel Charting with Spatial Distribution Map Matching
However, current channel-charting approaches lag behind fingerprinting in their positioning accuracy and still require reference samples for localization, regular data recording and labeling to keep the models up to date.
Reinforcement Learning for Node Selection in Branch-and-Bound
A big challenge in branch and bound lies in identifying the optimal node within the search tree from which to proceed.
C-MCTS: Safe Planning with Monte Carlo Tree Search
We propose Constrained MCTS (C-MCTS), which estimates cost using a safety critic that is trained with Temporal Difference learning in an offline phase prior to agent deployment.
Augmented Random Search for Multi-Objective Bayesian Optimization of Neural Networks
Deploying Deep Neural Networks (DNNs) on tiny devices is a common trend to process the increasing amount of sensor data being generated.
An Empirical Comparison of Optimizers for Quantum Machine Learning with SPSA-based Gradients
We introduce a novel approach that uses the approximated gradient from SPSA in combination with state-of-the-art gradient-based classical optimizers.
BCQQ: Batch-Constraint Quantum Q-Learning with Cyclic Data Re-uploading
Deep reinforcement learning (DRL) often requires a large number of data and environment interactions, making the training process time-consuming.
Quantum Natural Policy Gradients: Towards Sample-Efficient Reinforcement Learning
Reinforcement learning is a growing field in AI with a lot of potential.
Fusing Structure from Motion and Simulation-Augmented Pose Regression from Optical Flow for Challenging Indoor Environments
In this work, we propose recurrent fusion networks to optimally align absolute and relative pose predictions to improve the absolute pose prediction.
Representation Learning for Tablet and Paper Domain Adaptation in Favor of Online Handwriting Recognition
The goal of domain adaptation (DA) is to mitigate this domain shift problem by searching for an optimal feature transformation to learn a domain-invariant representation.
Just a Matter of Scale? Reevaluating Scale Equivariance in Convolutional Neural Networks
We also demonstrate that our family of models is able to generalize well towards larger scales and improve scale equivariance.
A Survey on Quantum Reinforcement Learning
Quantum reinforcement learning is an emerging field at the intersection of quantum computing and machine learning.
Indoor Localization with Robust Global Channel Charting: A Time-Distance-Based Approach
While CC has shown promising results in modelling the geometry of the radio environment, a deeper insight into CC for localization using multi-anchor large-bandwidth measurements is still pending.
Efficient Beam Search for Initial Access Using Collaborative Filtering
Our algorithm is based on a recommender system that associates groups (i. e., UEs) and preferences (i. e., beams from a codebook) based on a training data set.
Benchmarking Visual-Inertial Deep Multimodal Fusion for Relative Pose Regression and Odometry-aided Absolute Pose Regression
We show accuracy improvements for the APR-RPR task and for the RPR-RPR task for aerial vehicles and hand-held devices.
Active Learning of Ordinal Embeddings: A User Study on Football Data
We adapt an entropy-based active learning method with recent work from triplet mining to collect easy-to-answer but still informative annotations from human participants and use them to train a deep convolutional network that generalizes to unseen samples.
Driver Dojo: A Benchmark for Generalizable Reinforcement Learning for Autonomous Driving
Reinforcement learning (RL) has shown to reach super human-level performance across a wide range of tasks.
Complementary Semi-Deterministic Clusters for Realistic Statistical Channel Models for Positioning
The models that capture the physical effects observed in a realistic deployment scenario are essential for assessing the potential benefits of enhancements in positioning methods.
Towards Realistic Statistical Channel Models For Positioning: Evaluating the Impact of Early Clusters
Based on our measurement and simulation results, we propose a model for incorporating the signal reflection by obstacles in the vicinity of transmitter or receiver, so that the outcome of the model corresponds to the measurement made in such scenario.
Uncertainty-aware Evaluation of Time-Series Classification for Online Handwriting Recognition with Domain Shift
For many applications, analyzing the uncertainty of a machine learning model is indispensable.
Energy-efficient Deployment of Deep Learning Applications on Cortex-M based Microcontrollers using Deep Compression
Large Deep Neural Networks (DNNs) are the backbone of today's artificial intelligence due to their ability to make accurate predictions when being trained on huge datasets.
Incremental Data-Uploading for Full-Quantum Classification
Encoding high dimensional data into a quantum circuit for a NISQ device without any loss of information is not trivial and brings a lot of challenges.
Domain Adaptation for Time-Series Classification to Mitigate Covariate Shift
To mitigate this domain shift problem, domain adaptation (DA) techniques search for an optimal transformation that converts the (current) input data from a source domain to a target domain to learn a domain-invariant representation that reduces domain discrepancy.
Position Tracking using Likelihood Modeling of Channel Features with Gaussian Processes
We propose a novel localization framework that adapts well to sparse datasets that only contain CMs of specific areas within the environment with strong multipath propagation.
How to Learn from Risk: Explicit Risk-Utility Reinforcement Learning for Efficient and Safe Driving Strategies
This paper proposes SafeDQN, which allows to make the behavior of autonomous vehicles safe and interpretable while still being efficient.
An Introduction to Multi-Agent Reinforcement Learning and Review of its Application to Autonomous Mobility
Multi-Agent Reinforcement Learning (MARL) is a research field that aims to find optimal solutions for multiple agents that interact with each other.
Don't Get Me Wrong: How to Apply Deep Visual Interpretations to Time Series
Explanatory visual interpretation approaches for image, and natural language processing allow domain experts to validate and understand almost any deep learning model.
Auxiliary Cross-Modal Representation Learning with Triplet Loss Functions for Online Handwriting Recognition
We perform extensive evaluations on synthetic image and time-series data, and on data for offline handwriting recognition (HWR) and on online HWR from sensor-enhanced pens for classifying written words.
Benchmarking Online Sequence-to-Sequence and Character-based Handwriting Recognition from IMU-Enhanced Pens
While there exist many offline HWR datasets, there is only little data available for the development of OnHWR methods on paper as it requires hardware-integrated pens.
Uncovering Instabilities in Variational-Quantum Deep Q-Networks
In this work, we examine a class of hybrid quantum-classical RL algorithms that we collectively refer to as variational quantum deep Q-networks (VQ-DQN).
Objective Evaluation of Deep Visual Interpretations on Time Series Data
(Explanatory) visual interpretation approaches for image and natural language processing allow domain experts to validate and understand almost any deep learning model.
IALE: Imitating Active Learner Ensembles
Active learning (AL) prioritizes the labeling of the most informative data samples.
Deep Reinforcement Learning for Motion Planning of Mobile Robots
This paper presents a novel motion and trajectory planning algorithm for nonholonomic mobile robots that uses recent advances in deep reinforcement learning.
ViPR: Visual-Odometry-aided Pose Regression for 6DoF Camera Localization
Visual Odometry (VO) accumulates a positional drift in long-term robot navigation tasks.
Overcoming Catastrophic Forgetting via Hessian-free Curvature Estimates
Learning neural networks with gradient descent over a long sequence of tasks is problematic as their fine-tuning to new tasks overwrites the network weights that are important for previous tasks.
Self-Supervised Policy Adaptation
This generates pairs of state encodings, i. e., a new representation from the environment and a (biased) old representation from the forward model, that allow us to bootstrap a neural network model for state translation.
