astasik

• Stasik, Alexander Johannes; Hadzhamolla, Berk & Riemer-Sørensen, Signe (2026). Virtual Temperature Sensors in Power Transformers Using Neural Ordinary Differential Equations | PHM Society European Conference. Proceedings of the European Conference of the Prognostics and Health Management Society (PHME). 09(01). doi: 10.36001/phme.2026.v9i1.4991. Fulltekst i vitenarkiv Vis sammendrag

  Accurate modeling and forecasting of power transformer thermal behavior are critical for ensuring reliability, extending asset lifetime, and enabling optimized power system operation. Numerical approaches, such as finite element methods (FEM) and computational fluid dynamics (CFD), offer high fidelity but suffer from prohibitive computational costs, complex mesh generation, and limited feasibility in real-time or large scale applications, as well as often unknown geometries. Lumped-parameter thermal models provide a more practical alternative but depend on transformer-specific thermal constants and often fail to capture dynamic responses under varying operating and environmental conditions. Purely data-driven machine learning (ML) methods, including artificial neural networks (ANNs), convolutional neural networks (CNNs), and recurrent architectures such as long short-term memory (LSTM) networks, have shown success in forecasting transformer oil, winding, and hotspot temperatures; however, they typically require large volumes of high-quality training data and risk producing physically inconsistent or uninterpretable results. To overcome these limitations, hybrid frameworks such as physics-informed neural networks (PINNs) embed physical laws into the learning process, enabling physically consistent solutions while reducing data demands. This paper applies a physics-aware modeling of Neural Ordinary Differential Equations (Neural ODEs) adapted for forecasting transformer thermal behavior using real-world time-series data. Neural ODEs model system dynamics in continuous time, enabling smoother predictions, robustness to irregular sampling, and improved extrapolation capabilities compared to discrete-time models such as LSTMs. A key contribution of this work is the integration of simplified heat-transfer equations for power transformers directly into the Neural ODE, enabling a physics-aware formulation of the thermal dynamics. The model’s performance and generalization capabilities are evaluated across datasets from fifteen distinct transformers located in different regions of Norway, and characterized by varying designs and cooling mechanisms. The results demonstrate the success of the developed Neural ODEs framework to serve as a standardized, physics-aware, and robust forecasting tool for heterogeneous transformer units.

• Djupskås, Aslak; Riemer-Sørensen, Signe & Stasik, Alexander Johannes (2026). Unreliable Monte Carlo Dropout Uncertainty Estimation. Proceedings of Machine Learning Research (PMLR). 307, s. 106–114. doi: https:/proceedings.mlr.press/v307/djupskas26a.html. Fulltekst i vitenarkiv Vis sammendrag

  Reliable uncertainty estimation is crucial for machine learning models, especially in safety-critical domains. While exact Bayesian inference offers a principled approach, it is often computationally infeasible for deep neural networks. Monte Carlo dropout (MCD) was proposed as an efficient approximation to Bayesian inference in deep learning by applying neuron dropout at inference time [1]. Hence, the method generates multiple sub-models yielding a distribution of predictions to estimate uncertainty. We empirically investigate its ability to capture true uncertainty and compare to Gaussian Processes (GP) and Bayesian Neural Networks (BNN). We find that MCD struggles to accurately reflect the underlying true uncertainty, particularly failing to capture increased uncertainty in extrapolation and interpolation regions as observed in Bayesian models. The findings suggest that uncertainty estimates from MCD, as implemented and evaluated in these experiments, is not as reliable as those from traditional Bayesian approaches for capturing epistemic and aleatoric uncertainty.

• Hadzhamolla, Berk; Stasik, Alexander Johannes & Alaliyat, Saleh Abdel-Afou (2025). Modeling Dynamical Systems Using Neural ODEs: A Study On Scientific Machine Learning Models. I Scarpa, Marco; Cavalieri, Salvatore; Serrano, Salvatore & Vita, Fabrizio De (Red.), Proceedings of the 39th ECMS International Conference on Modelling and Simulation (ECMS 2025), June 24th - June 27th, 2025, Catania, Italy. ECMS European Council for Modelling and Simulation. ISSN 9783937436869. doi: 10.7148/2025-0704. Fulltekst i vitenarkiv Vis sammendrag

  This paper explores the application of Neural Ordinary Differential Equations (Neural ODEs) for modeling and simulating complex dynamic systems. We begin with the classical 1D harmonic oscillator to show how Neural ODEs can learn unknown system parameters and initial conditions directly from data, achieving accurate and robust performance under various external forces. Extending our investigation to the chaotic Lorenz system, we demonstrate the model’s capacity to capture highly nonlinear and sensitive dynamics. The results highlight the ability of Neural ODEs to approximate continuous trajectories adapt to long-term dependencies inherent in chaotic systems. Our experiments show that Neural ODEs can accurately model various dynamic systems, handle chaotic behavior, and adapt to external forces. These findings highlight the potential of Neural ODEs for improving the robustness and efficiency of hybrid machine learning models in scientific applications.

• Kulseng, Ola Tangen; Miao, Stanley; Fuchs, Franz Georg & Stasik, Alexander Johannes (2025). QuantumReservoirPy: A Software Package for Time Series Prediction. Journal of Open Source Software (JOSS). 10(110). doi: 10.21105/joss.07994. Fulltekst i vitenarkiv Vis sammendrag

  Reservoir computing on quantum computers has recently emerged as a potential resource for time series prediction, owing to its inherent complex dynamics. To advance Quantum Reservoir Computing (QRC) research, we have developed the Python package QuantumReservoirPy, which facilitates QRC using quantum circuits as reservoirs. The package is designed to be easy to use, while staying completely customizable. The resulting interface, similar to that of reservoirpy (Trouvain et al., 2020), simplifies the development of quantum reservoirs, and provides logical methods of comparison between reservoir architectures.

• Casolo, Simone; Stasik, Alexander Johannes; Zhang, Zhenyou & Riemer-Sørensen, Signe (2024). Testing Topological Data Analysis for Condition Monitoring of Wind Turbines. Proceedings of the European Conference of the Prognostics and Health Management Society (PHME). 8(1), s. 815–824. doi: 10.36001/phme.2024.v8i1.4117. Fulltekst i vitenarkiv
• Rimehaug, Atle Eskeland; Stasik, Alexander Johannes; Hagen, Espen; Billeh, Yazan N.; Siegle, Josh H. & Dai, Kael [Vis alle 10 forfattere av denne artikkelen] (2023). Uncovering circuit mechanisms of current sinks and sources with biophysical simulations of primary visual cortex. eLIFE. 12. doi: 10.7554/eLife.87169. Fulltekst i vitenarkiv Vis sammendrag

  Local field potential (LFP) recordings reflect the dynamics of the current source density (CSD) in brain tissue. The synaptic, cellular, and circuit contributions to current sinks and sources are ill-understood. We investigated these in mouse primary visual cortex using public Neuropixels recordings and a detailed circuit model based on simulating the Hodgkin–Huxley dynamics of >50,000 neurons belonging to 17 cell types. The model simultaneously captured spiking and CSD responses and demonstrated a two-way dissociation: firing rates are altered with minor effects on the CSD pattern by adjusting synaptic weights, and CSD is altered with minor effects on firing rates by adjusting synaptic placement on the dendrites. We describe how thalamocortical inputs and recurrent connections sculpt specific sinks and sources early in the visual response, whereas cortical feedback crucially alters them in later stages. These results establish quantitative links between macroscopic brain measurements (LFP/CSD) and microscopic biophysics-based understanding of neuron dynamics and show that CSD analysis provides powerful constraints for modeling beyond those from considering spikes.

• Skaar, Jan-Eirik Welle; Haug, Nicolai; Stasik, Alexander Johannes; Einevoll, Gaute & Tøndel, Kristin (2023). Metamodelling of a two-population spiking neural network. PLoS Computational Biology. ISSN 1553-734X. 19(11). doi: 10.1371/journal.pcbi.1011625. Fulltekst i vitenarkiv Vis sammendrag

  In computational neuroscience, hypotheses are often formulated as bottom-up mechanistic models of the systems in question, consisting of differential equations that can be numerically integrated forward in time. Candidate models can then be validated by comparison against experimental data. The model outputs of neural network models depend on both neuron parameters, connectivity parameters and other model inputs. Successful model fitting requires sufficient exploration of the model parameter space, which can be computationally demanding. Additionally, identifying degeneracy in the parameters, i.e. different combinations of parameter values that produce similar outputs, is of interest, as they define the subset of parameter values consistent with the data. In this computational study, we apply metamodels to a two-population recurrent spiking network of point-neurons, the so-called Brunel network. Metamodels are data-driven approximations to more complex models with more desirable computational properties, which can be run considerably faster than the original model. Specifically, we apply and compare two different metamodelling techniques, masked autoregressive flows (MAF) and deep Gaussian process regression (DGPR), to estimate the power spectra of two different signals; the population spiking activities and the local field potential. We find that the metamodels are able to accurately model the power spectra in the asynchronous irregular regime, and that the DGPR metamodel provides a more accurate representation of the simulator compared to the MAF metamodel. Using the metamodels, we estimate the posterior probability distributions over parameters given observed simulator outputs separately for both LFP and population spiking activities. We find that these distributions correctly identify parameter combinations that give similar model outputs, and that some parameters are significantly more constrained by observing the LFP than by observing the population spiking activities.

• Eidnes, Sølve; Stasik, Alexander Johannes; Sterud, Camilla; Bøhn, Eivind Eigil & Riemer-Sørensen, Signe (2023). Pseudo-Hamiltonian neural networks with state-dependent external forces. Physica D : Non-linear phenomena. ISSN 0167-2789. 446. doi: 10.1016/j.physd.2023.133673. Fulltekst i vitenarkiv Vis sammendrag

  Hybrid machine learning based on Hamiltonian formulations has recently been successfully demonstrated for simple mechanical systems, both energy conserving and not energy conserving. We introduce a pseudo-Hamiltonian formulation that is a generalization of the Hamiltonian formulation via the port-Hamiltonian formulation, and show that pseudo-Hamiltonian neural network models can be used to learn external forces acting on a system. We argue that this property is particularly useful when the external forces are state dependent, in which case it is the pseudo-Hamiltonian structure that facilitates the separation of internal and external forces. Numerical results are provided for a forced and damped mass–spring system and a tank system of higher complexity, and a symmetric fourth-order integration scheme is introduced for improved training on sparse and noisy data.

• Rimehaug, Atle Eskeland; Stasik, Alexander Johannes; Hagen, Espen; Siegle, Joshua H.; Dai, Kael & Olsen, Shawn R. [Vis alle 9 forfattere av denne artikkelen] (2022). Uncovering circuit mechanisms of current sinks and sources with biophysical simulations of primary visual cortex. BioRxiv. ISSN 0362-4331. doi: 10.1101/2022.02.22.481540. Fulltekst i vitenarkiv
• Skaar, Jan-Eirik Welle; Stasik, Alexander Johannes; Plesser, Hans Ekkehard; Einevoll, Gaute & Tøndel, Kristin (2022). Metamodelling of a two-population spiking neural network. BioRxiv. ISSN 0362-4331. doi: 10.1101/2022.09.05.506616. Fulltekst i vitenarkiv
• Fuchs, Franz Georg; Lye, Kjetil Olsen; Nilsen, Halvor Møll; Stasik, Alexander Johannes & Sartor, Giorgio (2022). Constraint Preserving Mixers for the Quantum Approximate Optimization Algorithm. Algorithms. 15(6). doi: 10.3390/a15060202. Fulltekst i vitenarkiv Vis sammendrag

  The quantum approximate optimization algorithm/quantum alternating operator ansatz (QAOA) is a heuristic to find approximate solutions of combinatorial optimization problems. Most of the literature is limited to quadratic problems without constraints. However, many practically relevant optimization problems do have (hard) constraints that need to be fulfilled. In this article, we present a framework for constructing mixing operators that restrict the evolution to a subspace of the full Hilbert space given by these constraints. We generalize the “XY”-mixer designed to preserve the subspace of “one-hot” states to the general case of subspaces given by a number of computational basis states. We expose the underlying mathematical structure which reveals more of how mixers work and how one can minimize their cost in terms of the number of CX gates, particularly when Trotterization is taken into account. Our analysis also leads to valid Trotterizations for an “XY”-mixer with fewer CX gates than is known to date. In view of practical implementations, we also describe algorithms for efficient decomposition into basis gates. Several examples of more general cases are presented and analyzed.

• Waszak, Maryna; Moen, Terje; Eidnes, Sølve; Stasik, Alexander Johannes; Hansen, Anders & Bouquet, Gregory [Vis alle 12 forfattere av denne artikkelen] (2022). Data quality issues for vibration sensors: a case study in ferrosilicon production. I Nguyen, Phu Hong; Magnanini, Maria Chiara & Sen, Sagar (Red.), Proceedings of the 2nd International Workshop on Software Engineering and AI for Data Quality in Cyber-Physical Systems/Internet of Things (SEA4DQ 2022). Association for Computing Machinery (ACM). ISSN 9781450394598. s. 22–23. doi: 10.1145/3549037.3561273. Fulltekst i vitenarkiv Vis sammendrag

  Digitisation in the mining and metal processing industries plays a key role in their modernisation. Production processes are more and more supported by a variety of sensors that produce large amounts of data that meant to provide insights into the performance of production infrastructures. In the metal processing industry vibration sensors are essential in the monitoring of the production infrastructure. In this position paper we present the installation of vibration sensors in a real industrial environment and discuss the data quality issues we encountered while using such sensors.

• Hagen, Espen; Chambers, Anna; Einevoll, Gaute; Pettersen, Klas Henning; Enger, Rune & Stasik, Alexander Johannes (2021). RippleNet: a Recurrent Neural Network for Sharp Wave Ripple (SPW-R) Detection. Neuroinformatics. ISSN 1539-2791. 19, s. 493–514. doi: 10.1007/s12021-020-09496-2. Fulltekst i vitenarkiv Vis sammendrag

  Hippocampal sharp wave ripples (SPW-R) have been identified as key bio-markers of important brain functions such as memory consolidation and decision making. Understanding their underlying mechanisms in healthy and pathological brain function and behaviour rely on accurate SPW-R detection. In this multidisciplinary study, we propose a novel, self-improving artificial intelligence (AI) detection method in the form of deep Recurrent Neural Networks (RNN) with Long Short-Term memory (LSTM) layers that can learn features of SPW-R events from raw, labeled input data. The approach contrasts conventional routines that typically relies on hand-crafted, heuristic feature extraction and often laborious manual curation. The algorithm is trained using supervised learning on hand-curated data sets with SPW-R events obtained under controlled conditions. The input to the algorithm is the local field potential (LFP), the low-frequency part of extracellularly recorded electric potentials from the CA1 region of the hippocampus. Its output predictions can be interpreted as time-varying probabilities of SPW-R events for the duration of the inputs. A simple thresholding applied to the output probabilities is found to identify times of SPW-R events with high precision. The non-causal, or bidirectional variant of the proposed algorithm demonstrates consistently better accuracy compared to the causal, or unidirectional counterpart. Reference implementations of the algorithm, named ‘RippleNet’, are open source, freely available, and implemented using a common open-source framework for neural networks (tensorflow.keras) and can be easily incorporated into existing data analysis workflows for processing experimental data.

• Geddes, Justen; Einevoll, Gaute; Acar, Evrim & Stasik, Alexander Johannes (2020). Multi-Linear Population Analysis (MLPA) of LFP Data Using Tensor Decompositions. Frontiers in Applied Mathematics and Statistics. doi: 10.3389/fams.2020.00041. Fulltekst i vitenarkiv Vis sammendrag

  The local field potential (LFP) is the low frequency part of the extracellular electrical potential in the brain and reflects synaptic activity onto thousands of neurons around each recording contact. Nowadays, LFPs can be measured at several hundred locations simultaneously. The measured LFP is in general a superposition of contributions from many underlying neural populations which makes interpretation of LFP measurements in terms of the underlying neural activity challenging. Classical statistical analyses of LFPs rely on matrix decomposition-based methods, such as PCA (Principal Component Analysis) and ICA (Independent Component Analysis), which require additional constraints on spatial and/or temporal patterns of populations. In this work, we instead explore the multi-fold data structure of LFP recordings, e.g., multiple trials, multi-channel time series, arrange the signals as a higher-order tensor (i.e., multiway array), and study how a specific tensor decomposition approach, namely canonical polyadic (CP) decomposition, can be used to reveal the underlying neural populations. Essential for interpretation, the CP model provides uniqueness without imposing constraints on patterns of underlying populations. Here, we first define a neural network model and based on its dynamics, compute LFPs. We run multiple trials with this network, and LFPs are then analysed simultaneously using the CP model. More specifically, we design feed-forward population rate neuron models to match the structure of state-of-the-art, large-scale LFP simulations, but downscale them to allow easy inspection and interpretation. We demonstrate that our feed-forward model matches the mathematical structure assumed in the CP model, and CP successfully reveals temporal and spatial patterns as well as variations over trials of underlying populations when compared with the ground truth from the model. We also discuss the use of diagnostic approaches for CP to guide the analysis when there is no ground truth information. In comparison with classical methods, we discuss the advantages of using tensor decompositions for analyzing LFP recordings as well as their limitations.

• Skaar, Jan-Eirik Welle; Stasik, Alexander Johannes; Hagen, Espen; Ness, Torbjørn V & Einevoll, Gaute (2020). Estimation of neural network model parameters from local field potentials (LFPs). PLoS Computational Biology. ISSN 1553-734X. 16(3). doi: 10.1371/journal.pcbi.1007725. Fulltekst i vitenarkiv Vis sammendrag

  Most modeling in systems neuroscience has been descriptive where neural representations such as ‘receptive fields’, have been found by statistically correlating neural activity to sensory input. In the traditional physics approach to modelling, hypotheses are represented by mechanistic models based on the underlying building blocks of the system, and candidate models are validated by comparing with experiments. Until now validation of mechanistic cortical network models has been based on comparison with neuronal spikes, found from the high-frequency part of extracellular electrical potentials. In this computational study we investigated to what extent the low-frequency part of the signal, the local field potential (LFP), can be used to validate and infer properties of mechanistic cortical network models. In particular, we asked the question whether the LFP can be used to accurately estimate synaptic connection weights in the underlying network. We considered the thoroughly analysed Brunel network comprising an excitatory and an inhibitory population of recurrently connected integrate-and-fire (LIF) neurons. This model exhibits a high diversity of spiking network dynamics depending on the values of only three network parameters. The LFP generated by the network was computed using a hybrid scheme where spikes computed from the point-neuron network were replayed on biophysically detailed multicompartmental neurons. We assessed how accurately the three model parameters could be estimated from power spectra of stationary ‘background’ LFP signals by application of convolutional neural nets (CNNs). All network parameters could be very accurately estimated, suggesting that LFPs indeed can be used for network model validation.

• Dai, Kael; Gratiy, Sergey L.; Billeh, Yazan; Xu, Richard; Cai, Binghuang & Cain, Nicholas [Vis alle 12 forfattere av denne artikkelen] (2020). Brain Modeling ToolKit: An open source software suite for multiscale modeling of brain circuits. PLoS Computational Biology. ISSN 1553-734X. 16(11). doi: 10.1371/journal.pcbi.1008386. Fulltekst i vitenarkiv Vis sammendrag

  Experimental studies in neuroscience are producing data at a rapidly increasing rate, providing exciting opportunities and formidable challenges to existing theoretical and modeling approaches. To turn massive datasets into predictive quantitative frameworks, the field needs software solutions for systematic integration of data into realistic, multiscale models. Here we describe the Brain Modeling ToolKit (BMTK), a software suite for building models and performing simulations at multiple levels of resolution, from biophysically detailed multi-compartmental, to point-neuron, to population-statistical approaches. Leveraging the SONATA file format and existing software such as NEURON, NEST, and others, BMTK offers a consistent user experience across multiple levels of resolution. It permits highly sophisticated simulations to be set up with little coding required, thus lowering entry barriers to new users. We illustrate successful applications of BMTK to large-scale simulations of a cortical area. BMTK is an open-source package provided as a resource supporting modeling-based discovery in the community.

• Hagen, Espen; Chambers, Anna; Einevoll, Gaute; Pettersen, Klas Henning; Enger, Rune & Stasik, Alexander Johannes (2020). RippleNet: A Recurrent Neural Network for Sharp Wave Ripple (SPW-R) Detection. BioRxiv. ISSN 0362-4331. doi: 10.1101/2020.05.11.087874. Fulltekst i vitenarkiv Vis sammendrag

  Hippocampal sharp wave ripples (SPW-R) have been identified as key bio-markers of important brain functions such as memory consolidation and decision making. SPW-R detection typically relies on hand-crafted feature extraction, and laborious manual curation is often required. In this multidisciplinary study, we propose a novel, self-improving artificial intelligence (AI) method in the form of deep Recurrent Neural Networks (RNN) with Long Short-Term memory (LSTM) layers that can learn features of SPW-R events from raw, labeled input data. The algorithm is trained using supervised learning on hand-curated data sets with SPW-R events. The input to the algorithm is the local field potential (LFP), the low-frequency part of extracellularly recorded electric potentials from the CA1 region of the hippocampus. The output prediction can be interpreted as the time-varying probability of SPW-R events for the duration of the input. A simple thresholding applied to the output probabilities is found to identify times of events with high precision. The reference implementation of the algorithm, named ‘RippleNet’, is open source, freely available, and implemented using a common open-source framework for neural networks (tensorflow.keras) and can be easily incorporated into existing data analysis workflows for processing experimental data.

Se alle arbeider i NVA

• Meltzer, Sunniva; Eidnes, Sølve & Stasik, Alexander Johannes (2026). Learning partially observed systems with neural Hamiltonian ordinary differential equations. Fulltekst i vitenarkiv
• Stasik, Alexander Johannes & Fuchs, Franz Georg (2026). Quantum random walks for decision making and optimization. doi: https:/sites.google.com/view/neqst-qc4ds-workshop-2026/home. Fulltekst i vitenarkiv Vis sammendrag

  Random walks provide a natural framework for modeling sequential discrete decision processes. Their quantum counterparts have been proposed as potential tools for addressing such problems, particularly if suitable oracles can be constructed to encode general loss functions over decision sequences. In this talk, we discuss perspectives on how quantum random walks could be applied to decision-making and optimization problems, and outline challenges and opportunities in oracle design.

• Halnes, Geir; Javaid, Anam; Solvang, Michael; Nichele, Stefano; Riegler, Michael & Singstad, Bjørn-Jostein [Vis alle 82 forfattere av denne artikkelen] (2025). Proceedings of NORA’s annual conference 2025. Nordic Machine Intelligence (NMI). 5(3), s. 1–14. doi: 10.5617/nmi.12551. Fulltekst i vitenarkiv
• Riemer-Sørensen, Signe; Stasik, Alexander Johannes; Hadzhamolla, Berk & Lund, Halvor (2025). Hybrid AI for power transformers​. Fulltekst i vitenarkiv
• Djupskås, Aslak; Stasik, Alexander Johannes & Riemer-Sørensen, Signe (2025). Unreliable Uncertainty Estimates with Monte Carlo Dropout. Fulltekst i vitenarkiv
• Leyos, Aaron de; Stasik, Alexander Johannes & Riemer-Sørensen, Signe (2025). Gaussian Process Kolmogorov-Arnold Networks for Probabilistic Multivariate Function Approximation. Fulltekst i vitenarkiv
• Stasik, Alexander Johannes & Bjervig, Joel (2025). AI-driven biological screening. Fulltekst i vitenarkiv
• Stasik, Alexander Johannes (2024). Reservoir computing: Possibilities and challenges. Fulltekst i vitenarkiv
• Riemer-Sørensen, Signe & Stasik, Alexander Johannes (2024). Hybrid AI for Energisektoren. Fulltekst i vitenarkiv
• Stasik, Alexander Johannes (2023). The Norwegian Quantum Landscape. Fulltekst i vitenarkiv
• Stasik, Alexander Johannes & Fuchs, Franz Georg (2023). QUantum reservoir computing. Fulltekst i vitenarkiv
• Eidnes, Sølve; Bøhn, Eivind Eigil; Lye, Kjetil Olsen; Myhr, Håkon Noren; Riemer-Sørensen, Signe & Stasik, Alexander Johannes [Vis alle 7 forfattere av denne artikkelen] (2023). Pseudo-Hamiltonian neural networks. Fulltekst i vitenarkiv
• Rimehaug, Atle Eskeland; Stasik, Alexander Johannes; Hagen, Espen; Billeh, Yazan; Siegle, Joshua H. & Dai, Kael [Vis alle 10 forfattere av denne artikkelen] (2022). Uncovering circuit mechanisms of current sinks and sources with biophysical simulations of primary visual cortex. Fulltekst i vitenarkiv
• Waszak, Maryna; Moen, Terje; Eidnes, Sølve; Stasik, Alexander Johannes; Hansen, Anders & Bouquet, Gregory [Vis alle 12 forfattere av denne artikkelen] (2022). Data quality issues for vibration sensors: a case study in ferrosilicon production. Fulltekst i vitenarkiv
• Riemer-Sørensen, Signe; Kjenstad, Dag & Stasik, Alexander Johannes (2022). Mer miljøvennlig transport med kunstig intelligens. [Journal]. Teknisk Ukeblad. Fulltekst i vitenarkiv Vis sammendrag

  Debattinnlegg

• Stasik, Alexander Johannes (2021). Quantum reservoir computing for machine learning. Fulltekst i vitenarkiv
• Stasik, Alexander Johannes (2020). Method of Blind Discovery Analyses Design at the Example of Neutrino Points Searches. Fulltekst i vitenarkiv
• Stasik, Alexander Johannes; Hagen, Espen; Skaar, Jan Eirik; Ness, Torbjørn V & Einevoll, Gaute (2019). Estimating parameters of biological neuronal networks using Convolutional Neural Networks. Fulltekst i vitenarkiv
• Hagen, Espen; Stasik, Alexander Johannes; Billeh, Yazan N.; Siegle, Joshua H.; Dai, Kael & Rimehaug, Atle Eskeland [Vis alle 14 forfattere av denne artikkelen] (2019). Comparing spikes and the local field potential (LFP) in V1 between experimental data and a comprehensive biophysical model. Fulltekst i vitenarkiv
• Hagen, Espen; Stasik, Alexander Johannes; Billeh, Yazan; Siegle, Joshua H.; Dai, Kael & Rimehaug, Atle Eskeland [Vis alle 14 forfattere av denne artikkelen] (2019). Comparing spikes and the local field potential (LFP) in V1 between experimental data and a comprehensive biophysical model. Fulltekst i vitenarkiv
• Stasik, Alexander Johannes; Hagen, Espen; Skaar, Jan Eirik; Ness, Torbjørn V & Einevoll, Gaute (2019). Estimating parameters of biological neuronal networks using Convolutional Neural Networks. Fulltekst i vitenarkiv
• Stasik, Alexander Johannes; Hagen, Espen; Skaar, Jan Eirik; Ness, Torbjørn V & Einevoll, Gaute (2019). Estimating parameters of biological neuronal networks using Convolutional Neural Networks. Fulltekst i vitenarkiv
• Stasik, Alexander Johannes (2019). What is machine learning and what does it have to do with statistics? Fulltekst i vitenarkiv
• Skaar, Jan-Eirik Welle; Hagen, Espen; Stasik, Alexander Johannes; Einevoll, Gaute & Ness, Torbjørn V (2018). Estimation of model parameters from LFPs of spiking neuron networks using deep learning. Fulltekst i vitenarkiv
• Dragly, Svenn-Arne; Mobarhan, Milad; Lepperød, Mikkel Elle; Tennøe, Simen; Stasik, Alexander Johannes & Fyhn, Marianne [Vis alle 8 forfattere av denne artikkelen] (2018). Exdir An alternative to HDF5 that uses Numpy files for data, YAML for metadata and simple directories to define the hierarchy. Fulltekst i vitenarkiv
• Stasik, Alexander Johannes; Mobarhan, Milad; Hagen, Espen & Einevoll, Gaute (2018). Generating Input from LGN for Simulation of Visual Cortex. Fulltekst i vitenarkiv
• Vang, Georg; Einevoll, Gaute Tomas; Stasik, Alexander Johannes & Beshkov, Kosio (2024). Exploration of reservoir computing and artificial neural network architectures as saliency detectors. Norges miljø- og biovitenskapelige universitet (NMBU). Fulltekst i vitenarkiv Vis sammendrag

  This study explores the performance of reservoir-type and conventional artificial neural networks as saliency detectors, inspired by Li Zhaoping's hypothesis regarding the V1's role as a saliency detector. A comparative analysis evaluates various models on a simple input image time series task, focusing on their effectiveness in training and out-of-sample validation data. Results indicate that while reservoir models exhibit higher training data loss compared to non-reservoir networks, they outperform other models on new data. Modifications to the reservoir structure show promise in improving both loss and Intersection over Union (IoU) score performance on the training and out-of-sample validation data. However, the study does not find that imposing a more visual cortex-like structure in the reservoir enhances its performance. Further analysis suggests that while reservoir models offer advantages such as cost-effectiveness and robustness for changes in input data, they may lack the precision of more trainable models like CNNs. Limitations to the thesis include the scope of hyperparameter exploration and the lack of overfitting mitigation techniques like the use of dropout. Future research should focus on refining all models to measure the potential performance on both training and out-of-sample data. This includes exploring ensemble methods and improving weight initialization techniques to enhance model precision and adaptability, leading to advancements in various real-world applications.

Se alle arbeider i NVA