Iskalni niz:
išči po
išči po
išči po
išči po
Vrsta gradiva:
Jezik:
Št. zadetkov: 4
Superposition and compression of deep neutral networks
Marko Zeman, Zoran Bosnić, Evgeny Osipov
Magistrsko delo
Oznake: artificial intelligence;machine learning;deep learning;convolutional neural networks;model compression;superposition of models;computer science;computer and information science;master's degree;
In this work we investigate a combination of the two recently proposed techniques: superposition of multiple neural networks into one and neural network compression. We show that these two techniques can be successfully combined to deliver a great potential for trimming down deep (convolutional) ne ...
Leto: 2020 Vir: Fakulteta za računalništvo in informatiko (UL FRI)
Discussion summarization using natural language processing techniques
VID STROPNIK, Zoran Bosnić, Evgeny Osipov
Diplomsko delo
Oznake: bstractive summarization;Online discussion summarization;Latent Dirchlet Allocation;Word embeddings;Hyperdimensional computing;Dimensionality reduction;Topic Labeling;Sentiment Analysis;
Discussions held on online forums differ from traditional text documents in several ways. In addition to individual utterances usually being very short, they also have multiple messengers, each of whom may exhibit their own form of non-natural punctuation and undocumented internet lingo use. Cons ...
Leto: 2020 Vir: Fakulteta za elektrotehniko (UL FE)
Improved mammography classification using data augmentation and transfer learning
Ana Peterka, Zoran Bosnić, Evgeny Osipov
Diplomsko delo
Oznake: artificial intelligence;machine learning;deep learning;convolutional neural networks;generative adversarial networks;mammography;cancer detection;computer science;computer and information science;computer science and mathematics;interdisciplinary studies;diploma;
Main goal of this thesis is to improve binary classification of mammograms, which could serve as a second opinion to the radiologists and give patients faster results. For this we studied the benefits of using data augmentation techniques and transfer learning. Training a deep convolutional neural n ...
Leto: 2022 Vir: Fakulteta za računalništvo in informatiko (UL FRI)
Problematika usklajevanja časa v protokolu MAC za brezžična senzorska omrežja
Jan Berdajs, Andrej Brodnik, Evgeny Osipov
Diplomsko delo
Oznake: brezžična senzorska omrežja;TinyOS;MAC protokol;HMAC protokol;sinhronizacija časa;zamik ure;FTSP;računalništvo;univerzitetni študij;diplomske naloge;
Problematika usklajevanja časa v protokolu MAC za brezžična senzorska omrežja
Leto: 2013 Vir: Fakulteta za računalništvo in informatiko (UL FRI)
Št. zadetkov: 4
Ključne besede:
Leto izdaje:
Avtorji:
Repozitorij:
Tipologija:
Jezik: