Sökning: "EMNIST"
Hittade 4 uppsatser innehållade ordet EMNIST.
1. IMPROVING THE PERFORMANCE OF DCGAN ON SYNTHESIZING IMAGES WITH A DEEP NEURO-FUZZY NETWORK
Kandidat-uppsats, Mälardalens universitet/Akademin för innovation, design och teknikSammanfattning : Since mid to late 2010 image synthesizing using neural networks has become a trending research topic. And the framework mostly used for solving these tasks is the Generative adversarial network (GAN). GAN works by using two networks, a generator and a discriminator that trains and competes alongside each other. LÄS MER
2. Investigation of generative adversarial network training : The effect of hyperparameters on training time and stability
Kandidat-uppsats, Högskolan i Skövde/Institutionen för informationsteknologiSammanfattning : Generative Adversarial Networks (GAN) is a technique used to learn the distribution of some dataset in order to generate similar data. GAN models are notoriously difficult to train, which has caused limited deployment in the industry. The results of this study can be used to accelerate the process of making GANs production ready. LÄS MER
3. Comparing Julia and Python : An investigation of the performance on image processing with deep neural networks and classification
Kandidat-uppsats, Blekinge Tekniska Högskola/Institutionen för programvaruteknikSammanfattning : Python is the most popular language when it comes to prototyping and developing machine learning algorithms. Python is an interpreted language that causes it to have a significant performance loss compared to compiled languages. LÄS MER
4. Effects of Transfer Learning on Data Augmentation with Generative Adversarial Networks
Kandidat-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : Data augmentation is a technique that acquires more training data by augmenting available samples, where the training data is used to fit model parameters. Data augmentation is utilized due to a shortage of training data in certain domains and to reduce overfitting. LÄS MER