Pattern learning
Dotaz
Zobrazit nápovědu
- MeSH
- krysa rodu rattus MeSH
- motivace MeSH
- odměna MeSH
- stravovací zvyklosti MeSH
- učení MeSH
- Check Tag
- krysa rodu rattus MeSH
Optimization of neural network topology, weights and neuron transfer functions for given data set and problem is not an easy task. In this article, we focus primarily on building optimal feed-forward neural network classifier for i.i.d. data sets. We apply meta-learning principles to the neural network structure and function optimization. We show that diversity promotion, ensembling, self-organization and induction are beneficial for the problem. We combine several different neuron types trained by various optimization algorithms to build a supervised feed-forward neural network called Group of Adaptive Models Evolution (GAME). The approach was tested on a large number of benchmark data sets. The experiments show that the combination of different optimization algorithms in the network is the best choice when the performance is averaged over several real-world problems.
Psychostimulancia, včetně metamfetaminu (MA), ovlivňují chování jedinců. U lidí navozují pozitivní emoce radost a štěstí, nebo potlačují negativní stavy typu anxiety či deprese. Test vyvýšeného křížového bludiště (elevated plus-maze, EPM) je nejčastěji používán k testování anxiolytických nebo anxiogenních látek, případně testování jednotlivých podtypů anxiogenních poruch. Úkolem této práce bylo otestovat vliv akutně podaného MA (1 mg/kg) na chování potkanů v EPM v protokolu s podrobnou analýzou všech vzorců chování podle studie Espejo (1998). Druhým cílem bylo zohlednit i vliv MA na učení a paméi! ve dvou fázích: akutně v „testu" a za 48 hodin a bez aplikace v „retestu". Naše výsledky ukazují, že MA ovlivňuje chování potkanů v EPM ve všech námi sledovaných kategoriích a neovlivnil učení. Prokázali jsme anxiogenní působení MA, zatímco učení nebylo M A výrazně ovlivněno.
Psychostimulants, including methamphetamine (MA), are known to influence behavior of individuals. In humans, psychostimulants i nduce positive emotions such as joy and happiness, or suppress unpleasant conditions such as anxiety and depression. Test of elevated plus-maze (EPM) is widely used test of anxiolytic and anxiogenic drugs, eventually examination of specific subtypes of anxiety disorders. The a im of the present work was to examine the effect of acutely applied MA (1 mg/kg) on rat behavior in the EPM. The detailed analysis of all behavio ral patterns was performed following the protocol based on the study of Espejo (1998). The original protocol was modified allowing to study the effect of MA on learning and memory. Our results demonstrated that MA affects rat behavior in the EPM in the most analyzed categories, al though it does not affect learning abilities. Therefor, the present protocol allowed us to determine positive anxiogenic effect of MA and exclude learning impairment.
- Klíčová slova
- anxieta, vyvýšené křížové bludiště, metamfetamin,
- MeSH
- bludiště - učení účinky léků MeSH
- chování MeSH
- financování organizované MeSH
- methamfetamin aplikace a dávkování škodlivé účinky MeSH
- modely u zvířat MeSH
- orientace účinky léků MeSH
- poruchy spojené s užíváním amfetaminu patofyziologie MeSH
- poruchy učení chemicky indukované patofyziologie MeSH
- potkani Wistar MeSH
- úzkost chemicky indukované MeSH
- zvířata MeSH
- Check Tag
- mužské pohlaví MeSH
- zvířata MeSH
To identify patterns in big medical datasets and use Deep Learning and Machine Learning (ML) to reliably diagnose Cardio Vascular Disease (CVD), researchers are currently delving deeply into these fields. Training on large datasets and producing highly accurate validation results is exceedingly difficult. Furthermore, early and precise diagnosis is necessary due to the increased global prevalence of cardiovascular disease (CVD). However, the increasing complexity of healthcare datasets makes it challenging to detect feature connections and produce precise predictions. To address these issues, the Intelligent Cardiovascular Disease Diagnosis based on Ant Colony Optimisation with Enhanced Deep Learning (ICVD-ACOEDL) model was developed. This model employs feature selection (FS) and hyperparameter optimization to diagnose CVD. Applying a min-max scaler, medical data is first consistently prepared. The key feature that sets ICVD-ACOEDL apart is the use of Ant Colony Optimisation (ACO) to select an optimal feature subset, which in turn helps to upgrade the performance of the ensuring deep learning enhanced neural network (DLENN) classifier. The model reforms the hyperparameters of DLENN for CVD classification using Bayesian optimization. Comprehensive evaluations on benchmark medical datasets show that ICVD-ACOEDL exceeds existing techniques, indicating that it could have a significant impact on CVD diagnosis. The model furnishes a workable way to increase CVD classification efficiency and accuracy in real-world medical situations by incorporating ACO for feature selection, min-max scaling for data pre-processing, and Bayesian optimization for hyperparameter tweaking.
- MeSH
- Bayesova věta MeSH
- deep learning * MeSH
- diagnóza počítačová metody MeSH
- Formicidae MeSH
- kardiovaskulární nemoci * diagnóza MeSH
- lidé MeSH
- neuronové sítě * MeSH
- Check Tag
- lidé MeSH
- Publikační typ
- časopisecké články MeSH
In this paper, we propose an integrated biologically inspired visual collision avoidance approach that is deployed on a real hexapod walking robot. The proposed approach is based on the Lobula giant movement detector (LGMD), a neural network for looming stimuli detection that can be found in visual pathways of insects, such as locusts. Although a superior performance of the LGMD in the detection of intercepting objects has been shown in many collision avoiding scenarios, its direct integration with motion control is an unexplored topic. In our work, we propose to utilize the LGMD neural network for visual interception detection with a central pattern generator (CPG) for locomotion control of a hexapod walking robot that are combined in the controller based on the long short-term memory (LSTM) recurrent neural network. Moreover, we propose self-supervised learning of the integrated controller to autonomously find a suitable setting of the system using a realistic robotic simulator. Thus, individual neural networks are trained in a simulation to enhance the performance of the controller that is then experimentally verified with a real hexapod walking robot in both collision and interception avoidance scenario and navigation in a cluttered environment.
- MeSH
- chování zvířat fyziologie MeSH
- chůze fyziologie MeSH
- kobylky fyziologie MeSH
- neuronové sítě MeSH
- řízené strojové učení MeSH
- robotika přístrojové vybavení MeSH
- učení vyhýbat se fyziologie MeSH
- zvířata MeSH
- Check Tag
- zvířata MeSH
- Publikační typ
- časopisecké články MeSH
- práce podpořená grantem MeSH
Animals demonstrate their ability to represent a geometric configuration of their environment and to use this information for spatial decisions in their response space in many situations. In presented experiment, we examined the ability of rats to interpret a configuration of abstract visual stimuli to make spatial decisions in a real response space. We tested whether they are able to interpret spatial configuration of abstract stimuli or whether they perceive such visual stimuli simply as geometric patterns associated to particular spatial choices. The rats were tested in a Skinner box with four nosing holes in the transparent front wall through which a computer screen was visible. According to the visual stimuli on the screen, the rats should choose the appropriate nosing hole to obtain a reward. We compared two groups of rats: the first group was exposed to the visual stimuli designed as a representation of the response space: the position of rewarded nosing hole was shown in relation to other nosing holes. The second group was exposed to one of four geometric patterns associated to one of the four nosing holes but without any implicit information about the response space. The results suggested that rats using the stimuli with information about configuration were significantly more successful than rats trained to respond to visual stimuli unrelated to the geometry of the environment.
- MeSH
- diskriminační učení fyziologie MeSH
- financování organizované MeSH
- krysa rodu rattus MeSH
- pochopení fyziologie MeSH
- potkani Long-Evans MeSH
- prostorové chování fyziologie MeSH
- rozpoznávání obrazu fyziologie MeSH
- výběrové chování fyziologie MeSH
- zraková percepce MeSH
- zvířata MeSH
- Check Tag
- krysa rodu rattus MeSH
- mužské pohlaví MeSH
- zvířata MeSH
- Publikační typ
- srovnávací studie MeSH
