Essays about: "CIFAR-10"
Showing result 16 - 20 of 26 essays containing the word CIFAR-10.
-
16. ERA: Evolution of Residual Architectures
University essay from Lunds universitet/Matematik LTHAbstract : This thesis investigates how well a neural architecture search can find competitive image classifiers on the CIFAR-10 data set with limited computational resources. Most work done on architecture search either uses vast computational resources or narrow and strongly informed space of possible solutions. READ MORE
-
17. Active Learning using a Sample Selector Network
University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)Abstract : In this work, we set the stage of a limited labelling budget and propose using a sample selector network to learn and select effective training samples, whose labels we would then acquire to train the target model performing the required machine learning task. We make the assumption that the sample features, the state of the target model and the training loss of the target model are informative for training the sample selector network. READ MORE
-
18. Enforcing low confidence class predictions for out of distribution data in deep convolutional networks
University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)Abstract : Modern discriminative deep neural networks are known to perform high confident predictions for inputs far away from the training data distribution, commonly referred to as out-of-distribution inputs. This property poses security concerns for the deployment of deep learning models in critical applications like autonomous vehicles because it hinders the detection of such inputs. READ MORE
-
19. Convolutional Neural Networks on FPGA and GPU on the Edge: A Comparison
University essay from Uppsala universitet/Signaler och systemAbstract : When asked to implement a neural network application, the decision concerning what hardware platform to use may not always be easily made. This thesis studies various relevant platforms with regards to performance, power efficiency and usability, with the purpose of providing a basis for such decisions. READ MORE
-
20. On the effectiveness of ß-VAEs for imageclassification and clustering : Using a disentangled representation for Transfer Learning and Semi-Supervised Learning
University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)Abstract : Data labeling is a critical and costly process, thus accessing large amounts of labeled data is not always feasible. Transfer Learning (TL) and Semi-Supervised Learning (SSL) are two promising approaches to leverage both labeled and unlabeled samples. READ MORE