Essays about: "Function Approximation"

Showing result 16 - 20 of 156 essays containing the words Function Approximation.

  1. 16. Thermoelectric measurements on InAs nanowires with a ratchet-barrier

    University essay from Lunds universitet/Fysiska institutionen; Lunds universitet/Fasta tillståndets fysik

    Author : Hanna Lundström; [2022]
    Keywords : Physics and Astronomy;

    Abstract : Efficient extraction of thermal energy from electrons at the micro- and nanoscale is a long-standing scientific goal that could enable novel types of heat engines, heat management, and solar cell applications. Semiconductor nanowires are a promising system for investigating such devices for several reasons, such as their thermoelectric properties, and the potential to be grown in heterostructures with high flexibility. READ MORE

  2. 17. Anomaly or not Anomaly, that is the Question of Uncertainty : Investigating the relation between model uncertainty and anomalies using a recurrent autoencoder approach to market time series

    University essay from Umeå universitet/Institutionen för datavetenskap

    Author : Anton Vidmark; [2022]
    Keywords : Uncertainty in deep learning; Bayesian; anomaly detection; novelty detection; stock market; time series;

    Abstract : Knowing when one does not know is crucial in decision making. By estimating uncertainties humans can recognize novelty both by intuition and reason, but most AI systems lack this self-reflective ability. In anomaly detection, a common approach is to train a model to learn the distinction between some notion of normal and some notion of anomalies. READ MORE

  3. 18. Exploring the column elimination optimization in LIF-STDP networks

    University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Author : Mingda Sun; [2022]
    Keywords : SpikingNeuralNetwork SNN ; neuromorphiccomputing; memoryoptimization; Hebbian learning; Spike-timing-depend plasticity STDP learning; Spiking Neural Network SNN ; neuromorphic computing; minnesoptimering; Hebbisk inlärning; spike-timing-depend plasticity STDP inlärning;

    Abstract : Spiking neural networks using Leaky-Integrate-and-Fire (LIF) neurons and Spike-timing-depend Plasticity (STDP) learning, are commonly used as more biological possible networks. Compare to DNNs and RNNs, the LIF-STDP networks are models which are closer to the biological cortex. READ MORE

  4. 19. Uncertainty quantification for neural network predictions

    University essay from Umeå universitet/Statistik

    Author : Jonas Borgström; [2022]
    Keywords : ;

    Abstract : Since their inception, machine learning methods have proven useful, and their usability continues to grow as new methods are introduced. However, as these methods are used for decision-making in most fields, such as weather forecasting,medicine, and stock market prediction, their reliability must be appropriately evaluated before the models are deployed. READ MORE

  5. 20. Simulation of a Battery Energy Storage System for Fast Frequency Reserve Support.

    University essay from Uppsala universitet/Institutionen för elektroteknik

    Author : Pathirage Dona Upekha Nimanthi Pathirage; [2022]
    Keywords : Energy Storage; Renewable Energy; Battery; Fast Frequency Reserve; Lithium-ion;

    Abstract : Electricity providers has a growing interest in moving towards Renewable Energy Sources (RES) for power generation due to their attractive features. This has caused phasing out of coal, oil and nuclear power plants which use large synchronous generators for power production. READ MORE