Sökning: "sparse representation"

Visar resultat 1 - 5 av 32 uppsatser innehållade orden sparse representation.

1. 1. Oligolectic bee species. An understudied group in Global Change impacts?

   Kandidat-uppsats, Göteborgs universitet / Instiutionen för biologi och miljövetenskap

   Författare :Monika Böttcher; [2024-03-19]
   Nyckelord :Solitary bee; global change; oligolecty; red list; taxonomy;

   Sammanfattning : Global change is considered the primary cause of the decline in bees worldwide, posing a significant threat to crucial pollination services they provide, carrying negative economic and ecological implications. Despite the extensive research conducted on the responses of bee communities to anthropogenic impacts, the focus has predominantly been on commercially interesting bees. LÄS MER

3. 2. Domain Adaptation Of Front View Synthetic Point Clouds Using GANs For Autonomous Driving

   Master-uppsats, KTH/Väg- och spårfordon samt konceptuell fordonsdesign

   Författare :Friedemann Kleinsteuber; [2023]
   Nyckelord :LiDAR; Domain Adaptation; GAN; CycleGAN; Simulation; LiDAR; Domänadaption; GAN; CycleGAN; Simulation;

   Sammanfattning : The perception of the environment is one of the main enablers of Autonomous Driving and is driven by Cameras, RADAR, and LiDAR sensors. Deep Learning algorithms used in perception need a vast amount of labeled, high-quality data which is costly to obtain for LiDAR sensors. LÄS MER

4. 3. MmWave Radar-based Deep Learning Collision Prediction

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

   Författare :Taylor Lauren V'dovec; [2023]
   Nyckelord :collision prediction; mmWave radar; deep learning; variational autoencoder VAE ; drone; autonomous navigation; kollisionsprognos; mmWave radar; djupinlärning; variational autoencoder VAE ; drönare; autonom navigation;

   Sammanfattning : Autonomous drone navigation in classical approaches typically involves constructing a map representation and employing path planning and collision checking algorithms within that map. Recently, novel deep learning techniques combined with depth camera observations have emerged as alternative approaches capable of achieving comparable collision-free performance. LÄS MER

5. 4. Modelling synaptic rewiring in brain-like neural networks for representation learning

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

   Författare :Kunal Bhatnagar; [2023]
   Nyckelord :Adaptive Sparsity; Computational Neuroscience; Rewiring; Structural Plasticity; Brain-like Computing; Neural Networks; Hebbian Learning; Adaptiv gleshet; beräkningsneurovetenskap; omkoppling; strukturell plasticitet; Hjärnliknande beräkning; Neurala Nätverk; Hebbskt lärande;

   Sammanfattning : This research investigated the concept of a sparsity method inspired by the principles of structural plasticity in the brain in order to create a sparse model of the Bayesian Confidence Propagation Neural Networks (BCPNN) during the training phase. This was done by extending the structural plasticity in the implementation of the BCPNN. LÄS MER

7. 5. Text Curation for Clustering of Free-text Survey Responses

   Master-uppsats, Linköpings universitet/Institutionen för datavetenskap

   Författare :Anton Gefvert; [2023]
   Nyckelord :Natural Language Processing; NLP; Sentence Representations; Sentence Representation Models; Survey; Surveys; Clustring;

   Sammanfattning : When issuing surveys, having the option for free-text answer fields is only feasible where the number of respondents is small, as the work to summarize the answers becomes unmanageable with a large number of responses. Using NLP techniques to cluster these answers and summarize them would allow a greater range of survey creators to incorporate free-text answers in their survey, without making their workload too large. LÄS MER