"neural networks (information technology)" - Selaus asiasanan mukaan Kandidaatintutkielmat
Viitteet 1-20 / 31
-
Acoustic Scene Classification with Interpretable Deep Neural Networks
(2024)
KandidaatintyöEnvironmental sounds are an important source of information, yet one that our devices commonly underutilize. While this has started to change in recent years with the growing interest in acoustic scene classification (ASC) ... -
Audio Similarity with Siamese Networks
(2023)
KandidaatintyöThe aim of this thesis was to study the application of Siamese neural networks to the problem of audio similarity measurement. A selection of Siamese networks with different architectures was presented and the results ... -
Automatic Assessment Of Parkinson’s Disease Using Spontaneous Speech
(2023)
KandidaatintyöParkinson's disease is a neurodegenerative disease with a range of symptoms, including speech impairments. These can be detected with digital signal processing, since speech signals carry paralinguistic information, which ... -
Automatic syllable count estimation from speech using neural network trained with a dsp-based estimator
(2023)
Valinnaisten aineopintojen tutkielmaAccurate syllable count estimation is crucial in various speech-related applications such as speech rate and rhythm analysis or language development research. However, it remains a challenging task to find cost-effective ... -
Automatic Text Generation Using Supervised Pre-training and Reinforcement Learning Based Adaptation
(2021)
KandidaatintyöText generation tasks are becoming more and more prominent in applications such as machine translation, image captioning, dialogue systems, etc. While text generation systems often require an extremely large amount of data, ... -
Comparative analysis of Neural Implicit Representation Methods for 3D Reconstruction
(2024)
KandidaatintyöIn recent years, advancements in artificial intelligence, robotics, augmented reality, and virtual reality have increased the volume of research that is done on one of the most intriguing topics in the field of computer ... -
Comparison of different features for neural network-based models in speaker identification
(2023)
KandidaatintyöThe general understanding in speech and audio processing has been that with larger datasets, task-specific features can be learned straight from a raw audio waveform, but with smaller datasets, traditional signal features, ... -
Cross-modal semantic retrieval in neural models of visually grounded speech
(2023)
KandidaatintyöMachine learning and its subset deep learning have been hot topics of technology for some years now. Visually grounded speech (VGS) models belong to a family of weakly supervised deep learning methods. The objective of VGS ... -
Data Acquisition for Forestry Scenes
(2023)
KandidaatintyöLarge quantities of samples are needed to train and benchmark today's data-driven machine-learning algorithms. Such well-established datasets for forestry scenes are scarce. This bachelor's thesis presents a simple, ... -
Dead reckoning with imu sensors : State-of-the-art
(2022)
Kandidaatintyö -
Deep Learning For Portfolio Optimization With Delta Controlled
(2022)
KandidaatintyöThe cryptocurrency market is considered high-risk compared to traditional investment channels such as stocks or bonds. The whole market trend is primarily affected by only a few top-of-the-market capitalization cryptocurrencies ... -
Deep Learning with Fourier Transformed Images
(2023)
KandidaatintyöThe research and applications based on deep learning have increased rapidly over the past years. Image classification is one of the main applicational scopes of deep learning. Many existing image classifiers are based on ... -
Early Detection of Dementia by Analysing Video Footage:Analysis of movement during instructionless viewing
(2023)
KandidaatintyöAs the population keeps ageing and the life-expectancy keeps rising, dementia is becoming more and more prevalent in society. Dementia slowly cripples the cognitive function of the patient, leading to memory issues and ... -
Harnessing neural networks for predicting next actions of investors
(2023)
KandidaatintyöThe goal of this study is to find out whether machine learning (ML) can be harnessed to predict next actions of active household investors. More precisely to compare the performance of three machine learning model structures. ... -
Image classification in the Fourier domain
(2024)
KandidaatintyöArtificial intelligence (AI) has recently gained a lot of attention in the media. The main driving force for emerging AI tools such as ChatGPT has been deep learning enabled by modern computational hardware. Deep learning ... -
Impact of Dataset Size in Large Language Model-Based Food-Disease Relation Detection
(2024)
KandidaatintyöUnderstanding relations between nutrients and diseases is important for healthcare advice and public health policies. Large amounts of such information is available in different scientific papers, but it is not easily ... -
Implementing a speech-to-text module for a conversational avatar
(2021)
KandidaatintyöMachine learning, or more specifically deep learning, has been gaining more and more popularity in complex computer science applications. One of these is speech recognition, where speech is translated into text by a computer. ... -
Implementing a text-to-speech module for a Deep Speaking Avatar
(2021)
KandidaatintyöThe aim of this project was to implement an end-to-end speech synthesis deep neural network, into a Deep Speaking Avatar project. Deep Speaking Avatar (DSA) is a character built using multiple deep neural networks (DNNs) ... -
Improving Code Quality Using Fine-tuning Large Language Models
(2024)
KandidaatintyöLarge language models has demonstrated significant capabilities in solving real-life problems by the means of generating human-like responses to input text in the similar format. However, these generic languages exhibit ... -
Learning privacy-preserving representation of audio data with adversarial learning: The usage of adversarial learning to address privacy problems in smart audio processing devices
(2023)
KandidaatintyöRecently, the development of IoT leads to numerous automated machine listening systems be ing introduced. In the audio signals processed by these systems, human voice also exists, which poses a threat of leakage of privacy ...
