Essays about: "Latent Utrymme"
Showing result 1 - 5 of 10 essays containing the words Latent Utrymme.
-
1. Distance preserving Fermat VAE
University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)Abstract : 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. READ MORE
-
2. Towards topology-aware Variational Auto-Encoders : from InvMap-VAE to Witness Simplicial VAE
University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)Abstract : 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. READ MORE
-
3. Attribute Embedding for Variational Auto-Encoders : Regularization derived from triplet loss
University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)Abstract : 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. READ MORE
-
4. Desert garden techniques to ameliorate urban microclimates : an example of application in Granada, Spain
University essay from SLU/Dept. of Landscape Architecture, Planning and Management (from 130101)Abstract : 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. READ MORE
-
5. Robust Descriptor Learning Using Variational Auto-Encoders
University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)Abstract : Image matching is the task of finding points in one image corresponding to the same points in the other image. Classical feature descriptors fail to match points when the images are under extreme viewpoint or seasonal changes. This thesis tackles the problem of image matching when two images are under severe changes. READ MORE