منابع مشابه
S-Map: A Network with a Simple Self-Organization Algorithm for Generative Topographic Mappings
The S-Map is a network with a simple learning algorithm that combines the self-organization capability of the Self-Organizing Map (SOM) and the probabilistic interpretability of the Generative Topographic Mapping (GTM). The simulations suggest that the SMap algorithm has a stronger tendency to self-organize from random initial configuration than the GTM. The S-Map algorithm can be further simpl...
متن کاملnetwork of phonological rules in lori dialect of andimeshk: a study within the framework of post-generative approach.
پژوهش حاضر ارائه ی توصیفی است از نظام آوایی گویش لری شهر اندیمشک، واقع در شمال غربی استان خوزستان. چهارچوب نظری این پژوهش، انگاره ی پسازایشی جزءمستقل می باشد. این پایان نامه شامل موارد زیر است: -توصیف آواهای این گویش به صورت آواشناسی سنتی و در قالب مختصه های زایشی ممیز، همراه با آوانوشته ی تفصیلی؛ -توصیف نظام آوایی گویش لری و قواعد واجی آن در چهارچوب انگاره ی پسازایشی جزءمستقل و معرفی برهم کن...
Wasserstein Generative Adversarial Network
Recent advances in deep generative models give us new perspective on modeling highdimensional, nonlinear data distributions. Especially the GAN training can successfully produce sharp, realistic images. However, GAN sidesteps the use of traditional maximum likelihood learning and instead adopts an two-player game approach. This new training behaves very differently compared to ML learning. Ther...
متن کاملControllable Generative Adversarial Network
Although it is recently introduced, in last few years, generative adversarial network (GAN) has been shown many promising results to generate realistic samples. However, it is hardly able to control generated samples since input variables for a generator are from a random distribution. Some attempts have been made to control generated samples from GAN, but they have shown moderate results. Furt...
متن کاملStyle Memory: Making a Classifier Network Generative
Deep networks have shown great performance in classification tasks. However, the parameters learned by the classifier networks usually discard stylistic information of the input, in favour of information strictly relevant to classification. We introduce a network that has the capacity to do both classification and reconstruction by adding a “style memory” to the output layer of the network. We ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Lecture Notes in Computer Science
سال: 2021
ISSN: ['1611-3349', '0302-9743']
DOI: https://doi.org/10.1007/978-3-030-90436-4_19