Blar i NTNU Open på forfatter "Tufte, Gunnar"
-
Evolving Artificial Spin Ice for Robust Computation
Penty, Arthur George; Tufte, Gunnar (Peer reviewed; Journal article, 2023)Artificial spin ice is a magnetic metamaterial showing particular promise as a novel substrate for unconventional computing. While simulations are invaluable for investigating new computational substrates, results must be ... -
Evolving Compositional Pattern Producing Networks For Cellular Automata Transition Rules
Ose, Mathias Berild (Master thesis, 2017)Traditional Cellular Automata (CA) transition rules are encoded as tables that grow quickly when the number of cell states or the size of the CA neighborhood increases. For methods that search for good transition rules, ... -
Evolving Music from a Self-Organising Nanomagnetic Orchestra
Penty, Arthur George; Tufte, Gunnar (Peer reviewed; Journal article, 2023) -
Exploring a Developmental Reservoir Computing System Using Self-Modifying Recurrent Cartesian Genetic Programming
Lima, Anders (Master thesis, 2017)Inspired by biology, numerous new computational models have been proposed as alternatives to cope with the ever-growing complexity of the traditional von Neumann architecture. Vastly parallel systems comprising simple units ... -
Exploring Physical Reservoir Computing using Random Boolean Networks.
Burkow, Aleksander Vognild (Master thesis, 2016)Reservoir computing (RC), a relatively new approach to machine learning, utilizes untrained recurrent neural networks as a reservoir of dynamics to pre-process some temporal task, making it separable with a linear readout ... -
Exploring Reservoir Computing with Spatial Constraints
Aven, Thomas (Master thesis, 2020)Reservoarberegning har blitt et fremtredende medlem av paradigmet for ukonvensjonell dataprosessering. Dette er et rammeverk velegnet for prosessering av tidsmessige og sekvensielle data, tradisjonelt ved bruk av rekurrente ... -
Flatspin: A large-scale artificial spin ice simulator
Jensen, Johannes Høydahl; Strømberg, Anders; Lykkebø, Odd Rune Strømmen; Penty, Arthur George; Lealiaert, Jonathan; Själander, Magnus; Folven, Erik; Tufte, Gunnar (Journal article; Peer reviewed, 2022)We present flatspin, a novel simulator for systems of interacting mesoscopic spins on a lattice, also known as artificial spin ice (ASI). A generalization of the Stoner-Wohlfarth model is introduced, and combined with a ... -
A general representation of dynamical systems for reservoir computing
Pontes-Filho, Sidney; Yazidi, Anis; Zhang, Jianhua; Hammer, Hugo Lewi; Mello, Gustavo; Sandvig, I.; Tufte, Gunnar; Nichele, Stefano (Chapter, 2019)Dynamical systems are capable of performing computation in a reservoir computing paradigm. This paper presents a general representation of these systems as an artificial neural network (ANN). Initially, we implement the ... -
Growing Cellular Structures with Substructures Guided by Genetic Algorithms: Using Visualization as Evaluation
Klakken, Trond (Master thesis, 2012)A dream about evolvable structures that change to fit its environment could be a peak into the future.Cellular automata (CA) being a simple discrete model, it has the ability to simulate biology by growing, reproducing and ... -
Implementation of a Multi-Channel 3D Audio Architecture
Bakkely, Christoffer (Master thesis, 2005)3D synthesis is the process where mono or stereo audio signal are rendered into audio with three dimensional qualities. By using these techniques it is possible to simulate natural audio by over a pair of stereo headphones. ... -
Implementing a Heterogeneous Multi-Core Prototype in an FPGA
Rusten, Leif Tore; Sortland, Gunnar Inge (Master thesis, 2012)Since the mid-1980s processor performance growth has been remarkable, with an annual growth of about 52 %. Methods such as architectural enhancements exploiting ILP and frequency scaling have been effective at increasing ... -
Inkrementell vekst av genomet for evolusjon av genotype representasjoner for kunstige cellulære organismer.
Giskeødegård, Andreas (Master thesis, 2013)I denne avhandlingen utforsker vi mulighetene for utvikling cellulær automat attraktorer i forskjellige størrelser med en algoritme som sakte utvider genotype av individer. Attraktorer av forskjellige størrelser er dyrket ... -
Interfacing Living Neural Cultures to Control a Robot
Naderi, Neshat (Master thesis, 2018)The idea of benefiting from exceptional capabilities of human cognition has been the inspiration to construct a bio-robotic machine.The human brain is an adaptive complex system capable of performing heavy computations ... -
Isolating the Black Box - Exploring the Effects of a Material Interface in Evolution in Materio
Lothe, Erik (Master thesis, 2015)Evolution in Materio (EiM) is the concept of exploiting intrinsic properties of various materials, or "black boxes", to perform computation. Motivation for EiM is multitudinous; new paradigms for computing, increased ... -
Konstruksjon av maskinvare for kjøring av sblokkbaserte eksperimenter
Djupdal, Asbjørn (Master thesis, 2003)En CompactPCI datamaskin med et NallaTech BenERA FPGA-kort har blitt kjøpt inn til bruk innen forskning på evolusjonær maskinvare. Denne datamaskinen er i stand til å rekonfigurere og kjøre en vilkårlig krets på en FPGA, ... -
Kunstig utvikling: Utvidelse av FPGA-basert SBlock-plattform
Aamodt, Kjetil (Master thesis, 2005)Utvikling av maskinvare foregår tradisjonelt med en topp-ned designstrategi. I fremtiden kan oppgavene som skal løses bli for kompliserte for denne utviklingsmetoden. En tilnærming som er foreslått er å benytte inspirasjon ... -
Machine Learning for Gesture Recognition with Electromyography
Chau, Tony (Master thesis, 2017)About 70 million deaf people use sign language as their first language or mother tongue, but the lack of a common language between the deaf and hearing individuals makes the general communication difficult. This thesis ... -
Maintaining Flipping Activity and Exploring Encoders for Reservoir Computing in Artificial Spin Ice
Engøy, Sindre (Master thesis, 2024)Reservoir Computing er en maskinlæringsparadigme innenfor feltet unconventional computing som utnytter komplekse fysiske system for beregning. Artifical spin ice et fysisk system som har vist seg å være et lovende materiale ... -
Model-Free All-Source-All-Destination Learning as a Model for Biological Reactive Control
Knudsen, Martinius; Hendseth, Sverre; Tufte, Gunnar; Sandvig, Axel (Journal article; Peer reviewed, 2021)We present here a model-free method for learning actions that lead to an all-source-all-destination shortest path solution. We motivate our approach in the context of biological learning for reactive control. Our method ... -
Model-free Control of Partially Observable Underactuated Systems by pairing Reinforcement Learning with Delay Embeddings
Knudsen, Martinius; Hendseth, Sverre; Tufte, Gunnar; Sandvig, Axel (Peer reviewed; Journal article, 2022)Abstract: Partial observability is a problem in control design where the measured states are insufficient in describing the systems trajectory. Interesting real-world systems often exhibit nonlinear behavior and noisy, ...