Sökning: "Activation patterns"
Visar resultat 1 - 5 av 43 uppsatser innehållade orden Activation patterns.
1. A Bayesian Bee Colony Algorithm for Hyperparameter Tuning of Stochastic SNNs : A design, development, and proposal of a stochastic spiking neural network and associated tuner
Uppsats för yrkesexamina på avancerad nivå, Uppsala universitet/Signaler och systemSammanfattning : With the world experiencing a rapid increase in the number of cloud devices, continuing to ensure high-quality connections requires a reimagining of cloud. One proponent, edge computing, consists of many distributed and close-to-consumer edge servers that are hired by the service providers. LÄS MER
2. Application of Physics-Informed Neural Networks for Galaxy Dynamics
Master-uppsats, Linnéuniversitetet/Institutionen för fysik och elektroteknik (IFE)Sammanfattning : Developing efficient and accurate numerical methods to simulate dynamics of physical systems has been an everlasting challenge in computational physics. Physics-Informed Neural Networks (PINNs) are neural networks that encode laws of physics into their structure. LÄS MER
3. The impact of ion drift in a Transcutaneous Electrical Stimulation model
Master-uppsats, Lunds universitet/Avdelningen för Biomedicinsk teknikSammanfattning : A major area of research in neuroscience is the effect of stimulating nerves into activation from extrinsic stimuli. This is commonly done with electric currents and external skin-contact electrodes. LÄS MER
4. Speaker verification: Advantages and limitations of a biologically inspired feature extractor
Master-uppsats, Lunds universitet/Institutionen för elektro- och informationsteknikSammanfattning : Speaker verification is the process of verifying the identity of a person based on voice. This process usually encompasses the following steps: The speech signal is mapped into features using a feature extractor, these features are then classified using a post processor. LÄS MER
5. An Empirical Study on the Generation of Linear Regions in ReLU Networks : Exploring the Relationship Between Data Topology and Network Complexity in Discriminative Modeling
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : The far-reaching successes of deep neural networks in a wide variety of learning tasks have prompted research on how model properties account for high network performance. For a specific class of models whose activation functions are piecewise linear, one such property of interest is the number of linear regions that the network generates. LÄS MER