|
|
Image Captioning with Recurrent Neural Networks
Kvita, Jakub ; Španěl, Michal (referee) ; Hradiš, Michal (advisor)
Tato práce se zabývá automatickým generovaním popisů obrázků s využitím několika druhů neuronových sítí. Práce je založena na článcích z MS COCO Captioning Challenge 2015 a znakových jazykových modelech, popularizovaných A. Karpathym. Navržený model je kombinací konvoluční a rekurentní neuronové sítě s architekturou kodér--dekodér. Vektor reprezentující zakódovaný obrázek je předáván jazykovému modelu jako hodnoty paměti LSTM vrstev v síti. Práce zkoumá, na jaké úrovni je model s takto jednoduchou architekturou schopen popisovat obrázky a jak si stojí v porovnání s ostatními současnými modely. Jedním ze závěrů práce je, že navržená architektura není dostatečná pro jakýkoli popis obrázků.
|
|
|
Human Activity Recognition Using Smartphone
Novák, Andrej ; Červenák, Rastislav (referee) ; Burget, Radim (advisor)
The increase of mobile smartphones continues to grow and with it the demand for automation and use of the most offered aspects of the phone, whether in medicine (health care and surveillance) or in user applications (automatic recognition of position, etc.). As part of this work has been created the designs and implementation of the system for the recognition of human activity on the basis of data processing from sensors of smartphones, along with the determination of the optimal parameters, recovery success rate and comparison of individual evaluation. Other benefits include a draft format and displaying numerous training set consisting of real contributions and their manual evaluation. In addition to the main benefits, the software tool was created to allow the validation of the elements of the training set and acquisition of features from this set and software, that is able with the help of deep learning to train models and then test them.
|
|
|
Methods of deep learning in image processing tasks
Polášková, Lenka ; Marcoň, Petr (referee) ; Mikulka, Jan (advisor)
The clue of learning to recognize objects using neural network lies in imitation of animal neural network's behavior. In spite the details of how brain works is not known yet, the teams consisting of scientists from various medical or technical professions are trying to search for them. Thanks to giants like Geoffrey Hinton science made a big progress in this domain. The convolutional networks which are based on animal model of optical system can be advantageously used for image segmentation and therefore they ware chosen for segmentation of tumor and edema from images of magnetic resonance. The models of artificial neural networks used in this work had achieved the 41\% of success in edema segmentation and 79\% in segmentation of tumor from brain issue.
|
|
|
Trainable image segmentation using deep neural networks
Majtán, Martin ; Burget, Radim (referee) ; Harár, Pavol (advisor)
Diploma thesis is aimed to trainable image segmentation using deep neural networks. In the paper is explained the principle of digital image processing and image segmentation. In the paper is also explained the principle of artificial neural network, model of artificial neuron, training and activation of artificial neural network. In practical part of the paper is created an algorithm of sliding window to generate sub-images from image from magnetic rezonance. Generated sub-images are used to train, test and validate of the model of neural network. In practical part of the paper si created the model of the artificial neural network, which is used to trainable image segmentation. Model of the neural network is created using the Deeplearning4j library and it is optimized to parallel training using Spark library.
|
|
|
Image classification using deep learning
Hřebíček, Zdeněk ; Přinosil, Jiří (referee) ; Mašek, Jan (advisor)
This thesis deals with image object detection and its classification into classes. Classification is provided by models of framework for deep learning BVLC/Caffe. Object detection is provided by AlpacaDB/selectivesearch and belltailjp/selective_search_py algorithms. One of results of this thesis is modification and usage of deep convolutional neural network AlexNet in BVLC/Caffe framework. This model was trained with precision 51,75% for classification into 1 000 classes. Then it was modified and trained for classification into 20 classes with precision 75.50%. Contribution of this thesis is implementation of graphical interface for object detction and their classification into classes, which is implemented as aplication based on web server in Python language. Aplication integrates object detection algorithms mentioned abowe with classification with help of BVLC/Caffe. Resulting aplication can be used for both object detection (and classification) and for fast verification of any classification model of BVLC/Caffe. This aplication was published on server GitHub under license Apache 2.0 so it can be further implemented and used.
|
|
|
Deep Learning for Image Recognition
Munzar, Milan ; Kolář, Martin (referee) ; Hradiš, Michal (advisor)
Neural networks are one of the state-of-the-art models for machine learning today. One may found them in autonomous robot systems, object and speech recognition, prediction and many others AI tasks. The thesis describes this model and its extension which is used in an object recognition. Then explains an application of a convolutional neural networks(CNNs) in an image recognition on Caltech101 and Cifar10 datasets. Using this exemplar application, the thesis discusses and measures efficiency of techniques used in CNNs. Results show that the convolutional networks without advanced extensions are able to reach a 80\% recognition accuracy on Cifar-10 and a 37\% accuracy on Caltech101.
|
|
|
Deep Neural Networks
Habrnál, Matěj ; Zbořil, František (referee) ; Zbořil, František (advisor)
The thesis addresses the topic of Deep Neural Networks, in particular the methods regar- ding the field of Deep Learning, which is used to initialize the weight and learning process s itself within Deep Neural Networks. The focus is also put to the basic theory of the classical Neural Networks, which is important to comprehensive understanding of the issue. The aim of this work is to determine the optimal set of optional parameters of the algori- thms on various complexity levels of image recognition tasks through experimenting with created application applying Deep Neural Networks. Furthermore, evaluation and analysis of the results and lessons learned from the experimentation with classical and Deep Neural Networks are integrated in the thesis.
|
|
|
Application of Mean Normalized Stochastic Gradient Descent for Speech Recognition
Klusáček, Jan ; Hradiš, Michal (referee) ; Pešán, Jan (advisor)
Umělé neuronové sítě jsou v posledních letech na vzestupu. Jednou z možných optimalizačních technik je mean-normalized stochastic gradient descent, který navrhli Wiesler a spol. [1]. Tato práce dále vysvětluje a zkoumá tuto metodu na problému klasifikace fonémů. Ne všechny závěry Wieslera a spol. byly potvrzeny. Mean-normalized SGD je vhodné použít pouze pokud je síť dostatečně velká, nepříliš hluboká a pracuje-li se sigmoidou jako nelineárním prvkem. V ostatních případech mean-normalized SGD mírně zhoršuje výkon neuronové sítě. Proto nemůže být doporučena jako obecná optimalizační technika. [1] Simon Wiesler, Alexander Richard, Ralf Schluter, and Hermann Ney. Mean-normalized stochastic gradient for large-scale deep learning. In Acoustics, Speech and Signal Processing (ICASSP), 2014 IEEE International Conference on, pages 180{184. IEEE, 2014.
|
|
|
Deep Learning for Image Recognition
Kozel, Michal ; Španěl, Michal (referee) ; Hradiš, Michal (advisor)
Neural networks are currently state-of-the-art technology for speech, image and other recognition tasks. This thesis describes basis properties of neural networks and their learning. The aim of this thesis was to extend Caffe framework with new learning methods and compare their performance on Cifar10 dataset. Namely RMSPROP and normalized SGD
|
|
|
Character recognition of real scenes using neural networks
Fiala, Petr ; Neumann, Lukáš (advisor) ; Berka, Petr (referee)
This thesis focuses on a problem of character recognition from real scenes, which has earned significant amount of attention with the development of modern technology. The aim of the paper is to use an algorithm that has state-of-art performance on standard data sets and apply it for the recognition task. The chosen algorithm is a convolution network with deep structure where the application of the specified model has not yet been published. The implemented solution is built on theoretical parts which are provided in comprehensive overview. Two types of neural network are used in the practical part: a multilayer perceptron and the convolution model. But as the complex structure of the convolution networks gives much better performance compare with the classification error of the MLP on the first data set, only the convolution structure is used in the further experiments. The model is validated on two public data sets that correspond with the specification of the task. In order to obtain an optimal solution based on the data structure several tests had been made on the modificated network and with various adjustments on the input data. Presented solution provided comparable prediction rate compare to the best results of the other studies while using artificially generated learning pattern. In conclusion, the thesis describes possible extensions and improvements of the model, which should lead to the decrease of the classification error.
|
guest ::
