Sökning: "Keras"

Visar resultat 21 - 25 av 54 uppsatser innehållade ordet Keras.

1. 21. Deep Learning Approach for Diabetic Retinopathy Grading with Transfer Learning

   Kandidat-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Författare :Linda Andersen; Philip Andersson; [2020]
   Nyckelord :;

   Sammanfattning : Diabetic retinopathy (DR) is a complication of diabetes and is a disease that affects the eyes. It is one of the leading causes of blindness in the Western world. As the number of people with diabetes grows globally, so does the number of people affected by diabetic retinopathy. LÄS MER

3. 22. Hyperparameters impact in a convolutional neural network

   Kandidat-uppsats, Högskolan i Skövde/Institutionen för informationsteknologi

   Författare :Andreas Bylund; Anton Erikssen; Drazen Mazalica; [2020]
   Nyckelord :Machine learning; Convolutional neural network; Traffic signs preprocessed; Hyperparameters; Supervised learning; Keras;

   Sammanfattning : Machine learning and image recognition is a big and growing subject in today's society. Therefore the aim of this thesis is to compare convolutional neural networks with different hyperparameter settings and see how the hyperparameters affect the networks test accuracy in identifying images of traffic signs. LÄS MER

4. 23. Transfer learning between domains : Evaluating the usefulness of transfer learning between object classification and audio classification

   Kandidat-uppsats, Högskolan i Skövde/Institutionen för informationsteknologi

   Författare :Tobias Frenger; Johan Häggmark; [2020]
   Nyckelord :Convolutional neural networks; Object classification; Audio classification; Transfer learning; Inception-V3; Inception-ResNet-V2; Keras; ImageNet; Mini-Inception; Mini-Inception-ResNet; Mel-spectrogram; CIFAR-10;

   Sammanfattning : Convolutional neural networks have been successfully applied to both object classification and audio classification. The aim of this thesis is to evaluate the degree of how well transfer learning of convolutional neural networks, trained in the object classification domain on large datasets (such as CIFAR-10, and ImageNet), can be applied to the audio classification domain when only a small dataset is available. LÄS MER

5. 24. Using deep learning to remove computed tomography artifacts due to hip replacement

   Master-uppsats, Lunds universitet/Matematik LTH

   Författare :Adelina Zahirovic; [2020]
   Nyckelord :Image analysis; Mathematics and Statistics;

   Sammanfattning : Computed Tomography (CT) is the most common diagnostic method for cancer and prostate cancer is the most common cancer among men in Sweden. Some of the patients that get scanned have hip replacements that cause artifacts in CT scans that make the CT images unreadable for physicians. LÄS MER

7. 25. Reinforcement Learning Methods for OpenAI Environments

   Kandidat-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Författare :Andreas Winberg; Oliver Öhrstam Lindström; [2020]
   Nyckelord :Reinforcement learning; Q-learning; OpenAIgym; neural networks;

   Sammanfattning : Using the powerful methods developed in the fieldof reinforcement learning requires an understanding of theadvantages and drawbacks of different methods as well as theeffects of the different adjustable parameters. This paper high-lights the differences in performance and applicability betweenthree different Q-learning methods: Q-table, deep Q-network anddouble deep Q-network where Q refers to the value assigned toa given state-action pair. LÄS MER