Sökning: "attractor"

Visar resultat 1 - 5 av 18 uppsatser innehållade ordet attractor.

1. 1. Hierarchical Clustering using Brain-like Recurrent Attractor Neural Networks

   Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Författare :Hannah Kühn; [2023]
   Nyckelord :Hierarchical Clustering; Attractor Network; Recurrent Neural Network; Brain-like computing; Hierarkisk klustring; Anlockningsnätverk; Återkommande neurala nätverk; Hjärnliknande databehandling;

   Sammanfattning : Hierarchical clustering is a family of machine learning methods that has many applications, amongst other data science and data mining. This thesis belongs to the research area of brain-like computing and introduces a novel approach to hierarchical clustering using a brain-like recurrent neural network. LÄS MER

3. 2. Mechatronic Bedbug Attractor : Attracting bedbugs using the principles of human breathing

   Magister-uppsats, KTH/Skolan för industriell teknik och management (ITM)

   Författare :Simon Lilja; Maja Åstrand; [2022]
   Nyckelord :Mechatronics; Simulated breathing; Bedbugs; Carbon dioxide; Solenoid valve.; Mekatronik; Simulerad andning; Vägglöss; Koldioxid; Magnetventil;

   Sammanfattning : Bedbugs are insects which exclusively feed on the blood of humans and other large animals. Bedbug infestations are a growing problem in modern society and some of the current solutions involve humans acting as bait to lure the bedbugs out of their nests. LÄS MER

4. 3. Role of Context in Episodic Memory : A Bayesian-Hebbian Neural Network Model of Episodic Recall

   Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Författare :Rohan Raj; [2022]
   Nyckelord :episodic memory; long-term memory; Bayesian Confidence Propagation Neural Network; synaptic plasticity; plasticity modulation; computational neuroscience;

   Sammanfattning : Episodic memory forms a fundamental aspect of human memory that accounts for the storage of events as well as the spatio-temporal relations between events during a lifetime. These spatio-temporal relations in which episodes are embedded can be understood as their contexts. Contexts play a crucial role in episodic memory retrieval. LÄS MER

5. 4. The Future of Office Space - Post the Covid-19 Pandemic : How Will the Current Pandemic Change Trends for Office Space? A Study Based on the Principal Actors Within the Industry

   Master-uppsats, KTH/Fastigheter och byggande

   Författare :Jasmin David; [2021]
   Nyckelord :Office; office space; trends; demand; Covid-19; pandemic; Kontor; kontorsyta; trender; efterfrågan; Covid-19; pandemi;

   Sammanfattning : During the last year and a half, the current Covid-19 pandemic has changed many aspects ofour lives, and while we cannot yet for sure say what changes are here to stay, we do knowthat we might expect a new everyday-normal. This study aims to investigate the future ofoffice space and whether we can expect a change in demand for the required space needed,and in addition, discover what trends are on the rise. LÄS MER

7. 5. Effects of Network Size in a Recurrent Bayesian Confidence Propagating Neural Network With two Synaptic Traces

   Kandidat-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Författare :William Laius Lundgren; Ludwig Karlsson; [2021]
   Nyckelord :BCPNN; computational brain modelling; shortterm memory; sequential learning; hypercolumns;

   Sammanfattning : A modular Recurrent Bayesian Confidence PropagatingNeural Networks (BCPNN) with two synaptic time tracesis a computational neural network that can serve as a modelof biological short term memory. The units in the network aregrouped into modules called hypercolumns within which there isa competitive winner-takes-all mechanism. LÄS MER