Sökning: "Latent Utrymme"
Visar resultat 1 - 5 av 20 uppsatser innehållade orden Latent Utrymme.
1. AI learn, AI do : En konstvetenskaplig studie om AI-modellers materialbetingade förmågor, aktörskap och deltagande inom konstnärliga processer
Master-uppsats, Uppsala universitet/Konstvetenskapliga institutionenSammanfattning : This master’s thesis investigates generative AI-art through the lens of actor network theory. By focusing on the role of images in datasets as a material that effects both AI-models and artworks, the decisively non-human agencies generative AI-models can be said to possess, and the traces and associations that generative AI-models imbue artworks with, this thesis aims to investigate art that has been created with GAN-models as well as contemporary text-to-image diffusion-models, by way of similar premises. LÄS MER
2. Distance preserving Fermat VAE
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : Deep neural networks takes their strength in the representations, or features, that they internally build. While these internal encodings help networks performing classification or regression tasks on specific data types, it exists a branch of machine learning that has for only purpose to build these representations. LÄS MER
3. Towards topology-aware Variational Auto-Encoders : from InvMap-VAE to Witness Simplicial VAE
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : Variational Auto-Encoders (VAEs) are one of the most famous deep generative models. After showing that standard VAEs may not preserve the topology, that is the shape of the data, between the input and the latent space, we tried to modify them so that the topology is preserved. LÄS MER
4. Attribute Embedding for Variational Auto-Encoders : Regularization derived from triplet loss
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : Techniques for imposing a structure on the latent space of neural networks have seen much development in recent years. Clustering techniques used for classification have been used to great success, and with this work we hope to bridge the gap between contrastive losses and Generative models. LÄS MER
5. Desert garden techniques to ameliorate urban microclimates : an example of application in Granada, Spain
Master-uppsats, SLU/Dept. of Landscape Architecture, Planning and Management (from 130101)Sammanfattning : In this day and age we are faced with urban cores getting hotter, with the main drivers being climate change and the urban heat island effect. This gets even more complicated as the parts of Europe that have the largest need too cool down, i.e. the south, has the least amount of space available for interventions in the form of green space. LÄS MER