|
|
Pupil activation in relation to group work in biology lessons
Janovska, Kateřina ; Rajsiglová, Ina (advisor) ; Blažová, Kateřina (referee)
The bachelor's thesis "Student activation in relation to group work in biology lessons" discusses the essence of student activation and the importance of group work with elements of cooperation. The work contains the definition of activation, active learning, group cooperation and work in it. It gives examples of models and methods supporting student activation, which are also suitable for group work in biology lessons. Among other things, it points to the use of these models and methods as support in schools in the post-covid period. Keywords Student activation, active learning, activation methods, constructivism, models of teaching, group work
|
|
|
Computer Vision with Active Learning
Kolář, Martin ; Machová, Kristína (referee) ; Arridge, Simon (referee) ; Zemčík, Pavel (advisor)
Metody strojového vidění se zdokonalují zlepšením modelů, laděním trénovaných parametrů nebo anotací reprezentativních dat. Tato práce řadou experimentů potvrzuje hypotézu že aktivní učení zvyšuje přesnost těchto modelů. Rozšířením přistupu pseudolabelů o aktivní učení přispívá tato práce přístupem "one-shot-learning" k učení nových kategorií obrazů s použitím algoritmických doporučení, dále online grafickým uživatelským rozhraním pro optimalizaci dilema Exploration/Exploitation pro online tagování, a dvoukrokovým offline binárním přístupem aktivního učení pro zlepšení kvality dat používaných pro snímání fontů. Tím, že demonstruje přínos aktivního učení v těchto přístupech, přispívá tato práce k hypotéze i konkrétním aplikacím strojového vidění.
|
|
|
Active learning for Bayesian neural networks in image classification
Belák, Michal ; Šabata, Tomáš (advisor) ; Vomlelová, Marta (referee)
In the past few years, complex neural networks have achieved state of the art results in image classification. However, training these models requires large amounts of labelled data. Whereas unlabelled images are often readily available in large quantities, obtaining l abels takes considerable human effort. Active learning reduces the required labelling effort by selecting the most informative instances to label. The most popular active learning query strategy framework, uncertainty sampling, uses uncertainty estimates of the model being trained to select instances for labelling. However, modern classification neural networks often do not provide good uncertainty estimates. Baye sian neural networks model uncertainties over model parameters, which can be used to obtain uncertainties over model predictions. Exact Bayesian inference is intractable for neural networks, however several approximate methods have been proposed. We experiment with three such methods using various uncertainty sampling active learning query strategies.
|
|
|
Historical curriculum at primary school
Šulcová, Jana ; Dvořáková, Michaela (advisor) ; Stará, Jana (referee)
This thesis discusses the historical curriculum in primary school and looking for ways to teach it effectively. Its aim is to analyze the educational goals of the historical curriculum of primary school. The introduction deals with the question of why history should be part of education in the first grade of primary school. Furthermore, it compares the historical conception of education at primary school in our conditions with the concept of the state, whose aims and methods of historical thinking are inspiring for us. Based on the findings and recommendations of domestic and foreign researches are in the empirical part of the thesis didactic designed tutorials selected topic historical subject matter with regard to diagnosis and development of historical thinking. Proposed lessons were implemented in the second year of primary school. At the end of each lesson is to evaluate the effectiveness of proposed schemes through analysis worksheets and comparing the results of the input and output mind maps and chalk talk. The entire set of lessons is evaluated through analysis of the final evaluation sheets pupils.
|
|
| |
|
| |
|
|
Active Learning for Processing of Archive Sources
Hříbek, David ; Zbořil, František (referee) ; Rozman, Jaroslav (advisor)
This work deals with the creation of a system that allows uploading and annotating scans of historical documents and subsequent active learning of models for character recognition (OCR) on available annotations (marked lines and their transcripts). The work describes the process, classifies the techniques and presents an existing system for character recognition. Above all, emphasis is placed on machine learning methods. Furthermore, the methods of active learning are explained and a method of active learning of available OCR models from annotated scans is proposed. The rest of the work deals with a system design, implementation, available datasets, evaluation of self-created OCR model and testing of the entire system.
|
|
|
Active learning for Bayesian neural networks in image classification
Belák, Michal ; Šabata, Tomáš (advisor) ; Vomlelová, Marta (referee)
In the past few years, complex neural networks have achieved state of the art results in image classification. However, training these models requires large amounts of labelled data. Whereas unlabelled images are often readily available in large quantities, obtaining l abels takes considerable human effort. Active learning reduces the required labelling effort by selecting the most informative instances to label. The most popular active learning query strategy framework, uncertainty sampling, uses uncertainty estimates of the model being trained to select instances for labelling. However, modern classification neural networks often do not provide good uncertainty estimates. Baye sian neural networks model uncertainties over model parameters, which can be used to obtain uncertainties over model predictions. Exact Bayesian inference is intractable for neural networks, however several approximate methods have been proposed. We experiment with three such methods using various uncertainty sampling active learning query strategies.
|
|
|
Active Learning with Neural Networks
Bureš, Tomáš ; Kolář, Martin (referee) ; Hradiš, Michal (advisor)
The topic of this thesis in active learning in conjunction with neural networks. First, it deals with theory of active learning and strategies used in real life scenarios. Followed by practical part, experimenting with active learning strategie and evaluating those experiments.
|
|
|
Active Learning for OCR
Kohút, Jan ; Kolář, Martin (referee) ; Hradiš, Michal (advisor)
The aim of this Master's thesis is to design methods of active learning and to experiment with datasets of historical documents. A large and diverse dataset IMPACT of more than one million lines is used for experiments. I am using neural networks to check the readability of lines and correctness of their annotations. Firstly, I compare architectures of convolutional and recurrent neural networks with bidirectional LSTM layer. Next, I study different ways of learning neural networks using methods of active learning. Mainly I use active learning to adapt neural networks to documents that the neural networks do not have in the original training dataset. Active learning is thus used for picking appropriate adaptation data. Convolutional neural networks achieve 98.6\% accuracy, recurrent neural networks achieve 99.5\% accuracy. Active learning decreases error by 26\% compared to random pick of adaptations data.
|
guest ::
