Search results for "Neural Networks"
showing 10 items of 599 documents
Convolutional Neural Network With Shape Prior Applied to Cardiac MRI Segmentation.
2019
In this paper, we present a novel convolutional neural network architecture to segment images from a series of short-axis cardiac magnetic resonance slices (CMRI). The proposed model is an extension of the U-net that embeds a cardiac shape prior and involves a loss function tailored to the cardiac anatomy. Since the shape prior is computed offline only once, the execution of our model is not limited by its calculation. Our system takes as input raw magnetic resonance images, requires no manual preprocessing or image cropping and is trained to segment the endocardium and epicardium of the left ventricle, the endocardium of the right ventricle, as well as the center of the left ventricle. Wit…
Mašīnmācīšanās uzdevumu risināšanai interaktīvās tekstuālās vidēs
2021
Interaktīvas tekstuālas piedzīvojumu spēles var izmantot, lai pārbaudītu mašīnmācīšanās aģentu spējas tikt galā ar dažādiem izaicinājumiem, kas saistīti ar dabiskās valodas izpratni, problēmu risināšanu un atbilžu meklēšanu, vai tādas darbības izvēles stratēģiju apgūšana, kas vispārinās uz iepriekš nesastaptām vidēm. TextWorld platforma ir šādiem pētījumiem domāts ietvars un palīgrīki, ar kuru palīdzību var darbināt daudzas iepriekšpublicētas teksta piedzīvojumu spēles, vai arī definēt un ģenerēt jaunas spēles, dažādās sarežģītības pakāpēs un gandrīz bezgalīgās variācijās. Šajā darbā aprakstīta tāda algoritmiska orākula (oracle) ieviešana, kas var veiksmīgi atrisināt spēles no 3 dažādām iep…
Mašīnmācīšanās pielietojums sporta notikumu prognozēšanā
2017
Dažādu notikumu prognozēšana cilvēcei ir vienmēr bijusi aktuāla. Mūsdienās ir attīstījušās tehnoloģijas, lai to būtu iespējams paveikt balstoties uz pagātnes datiem. Darbā tiek apskatīta sporta notikumu prognozēšana, konkrēti futbola maču iznākumi. Tiek apskatītas vairākas mašīnmācīšanās metodes, kas būtu piemērotākās šī uzdevuma veikšanai. Tiek realizēti un optimizēti divi multi-slāņu perceptrona tīkli un viens vairākkārtējā neironu tīkla, konkrēti LSTM algoritms. Ar tiem tiek veikta simulācija izmantojot reālus datus. Vienā no simulācijām tiek sasniegts pozitīvs rezultāts, sezonas laikā algoritms gūst 65% peļņu.
A Simple and Efficient Deep Learning-Based Framework for Automatic Fruit Recognition
2022
Accurate detection and recognition of various kinds of fruits and vegetables by using the artificial intelligence (AI) approach always remain a challenging task due to similarity between various types of fruits and challenging environments such as lighting and background variations. Therefore, developing and exploring an expert system for automatic fruits’ recognition is getting more and more important after many successful approaches; however, this technology is still far from being mature. The deep learning-based models have emerged as state-of-the-art techniques for image segmentation and classification and have a lot of promise in challenging domains such as agriculture, where they can …
A sentence based system for measuring syntax complexity using a recurrent deep neural network
2018
In this paper we present a deep neural network model capable of inducing the rules that identify the syntax complexity of an Italian sentence. Our system, beyond the ability of choosing if a sentence needs of simplification, gives a score that represent the confidence of the model during the process of decision making which could be representative of the sentence complexity. Experiments have been carried out on one public corpus created specifically for the problem of text-simplification.
A recurrent deep neural network model to measure sentence complexity for the Italian Language
2019
Text simplification (TS) is a natural language processing task devoted to the modification of a text in such a way that the grammar and structure of the phrases is greatly simplified, preserving the underlying meaning and information contents. In this paper we give a contribution to the TS field presenting a deep neural network model able to detect the complexity of italian sentences. In particular, the system gives a score to an input text that identifies the confidence level during the decision making process and that could be interpreted as a measure of the sentence complexity. Experiments have been carried out on one public corpus of Italian texts created specifically for the task of TS…
Mapping and holistic design of natural hydraulic lime mortars
2020
Supplementary data to this article can be found online at https://doi.org/10.1016/j.cemconres.2020.106167.
Generative Adversarial Networks in Cardiology
2021
A B S T R A C T Generative Adversarial Networks (GANs) are state-of-the-art neural network models used to synthesize images and other data. GANs brought a considerable improvement to the quality of synthetic data, quickly becoming the standard for data generation tasks. In this work, we summarize the applications of GANs in the field of cardiology, including generation of realistic cardiac images, electrocardiography signals, and synthetic electronic health records. The utility of GAN-generated data is discussed with respect to research, clinical care, and academia. Moreover, we present illustrative examples of our GAN-generated cardiac magnetic resonance and echocardiography images, showin…
Capabilities of Ultrametric Automata with One, Two, and Three States
2016
Ultrametric automata use p-adic numbers to describe the random branching of the process of computation. Previous research has shown that ultrametric automata can have a significant decrease in computing complexity. In this paper we consider the languages that can be recognized by one-way ultrametric automata with one, two, and three states. We also show an example of a promise problem that can be solved by ultrametric integral automaton with three states.
On the Hierarchy Classes of Finite Ultrametric Automata
2015
This paper explores the language classes that arise with respect to the head count of a finite ultrametric automaton. First we prove that in the one-way setting there is a language that can be recognized by a one-head ultrametric finite automaton and cannot be recognized by any k-head non-deterministic finite automaton. Then we prove that in the two-way setting the class of languages recognized by ultrametric finite k-head automata is a proper subclass of the class of languages recognized by (k + 1)-head automata. Ultrametric finite automata are similar to probabilistic and quantum automata and have only just recently been introduced by Freivalds. We introduce ultrametric Turing machines an…