Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 20 of 36 for “"Unsupervised training"”.
-
AN IMPROVED UNSUPERVISED TRAINING ALGORITHM FOR NEOCOGNITRON
… computer simulations, we have investigated the unsupervised training algorithm of neocognitron. We observed that extended and strong features such as line segments are extracted in the intermediate stages, due to a positive feedback effect in the training algorithm. We then propose a refined …
-
Supervised and unsupervised training of deep autoencoder
… network to learn complex patterns in data. As training a multiple layer neural network is time consuming, a pre-training step has been employed to initialize the weights of a deep network to speed up the training process. In the pre-training step, each layer is trained individually and the …
-
Unsupervised training methods for non-intrusive appliance load monitoring from smart meter data
… Existing approaches to NIALM require a manual training phase in which either sub-metered appliance data is collected or appliance usage is manually labelled. This training data is used to build models of the house- hold appliances, which are subsequently used to disaggregate the household’s …
-
Unsupervised and semi-supervised training methods for eukaryotic gene prediction
… validated set of genes or gene elements. These training sets often require time and additional expert efforts especially for the species that are in the initial stages of genome sequencing. Unsupervised training allows determination of model parameters from anonymous genomic sequence with. The …
-
Spatiotemporal Pattern Detection with Neuromorphic Circuits
… in order to detect spatiotemporal patterns. Unsupervised training and detection-by-design techniques were used to attain the appropriate connectomes and perform pattern detection. Unsupervised training was performed by feeding random digital spikes with a repeating embedded spatiotemporal …
-
A STUDY ON RECEIVED SIGNAL STRENGTH BASED INDOOR LOCALIZATION
… LOCALIZATION, I.E. ACCURACY IMPROVEMENT, TRAINING COST ELIMINATION, AND ROBUSTNESS ENHANCEMENT. FIRST, WE HAVE DEVELOPED TWO NEW APPROACHES TO ENHANCE THE ACCURACY, I.E. FUSION APPROACH AND STATISTICAL APPROACH. SECOND, WE HAVE DERIVED AN UNSUPERVISED TRAINING ALGORITHM TO REDUCE THE …
-
Recurrent Neural Network for Learning Spatial and Temporal Information from Videos
… camera pose estimation with an end-to-end unsupervised training scheme which relies on a recurrent based pose estimator. We illustrate the contribution of recurrent estimation (a.k.a step-by-step estimation) in the estimation of large displacements and complex transformations. We also show …
-
Protein thermostability prediction using sequence representations from protein language models /
… of language components - are created during the unsupervised training. Embeddings can be transferred as input to other models to solve the required tasks using the supervised learning. The main idea of this work is a collection of feed-forward neural networks, which take embeddings from protein …
-
Improvement of ab initio methods of gene prediction in genomic and metagenomic sequences
… ways of parameter estimation such as supervised training on a set of validated genes or unsupervised training on an anonymous sequence supposed to contain a large enough number of genes. The codon frequencies, critical for the model parameterization, could be derived from frequencies of …
-
Convex Large Margin Training - Unsupervised, Semi-supervised, and Robust Support Vector Machines
… a decade. The intuitive principle behind SVM training is to find the maximum margin separating hyperplane for a given set of binary labeled training data. Previously, SVMs have been primarily applied to supervised learning problems, where target class labels are provided with the data. …
-
Efficient Deep Neural Networks for Autonomous Perception
… estimators, including eSURE and ePURE, enabling unsupervised training of deep neural networks for magnetic resonance image denoising under Gaussian and Poisson noise. However, these methods rely on known noise assumptions, which motivates the second contribution: a unified diffusion and Bayesian …
-
Assisting Unsupervised Optical Flow Estimation with External Information
… Due to the scarcity of ground-truth labels, the unsupervised estimation of optical flow is especially important. However, it is a poorly constrained problem and presents challenges in the presence of occlusions, motion boundaries, non-Lambertian surfaces, lack of texture, and illumination …
-
Controllable Simulation of Deformable Motion in Cone-Beam Computed Tomography with Generative Learned Models
… motion of adjustable magnitude, through unsupervised training using the observation of unpaired, motion-corrupted data. Evaluation of this model in a proof-of-concept study demonstrated three main features of the generated motion fields. First, the agreement between the spatial …
-
Lecture transcription systems in resource–scarce environments
… for alignment. Another approach entails using unsupervised training methods where an initial low accuracy recognizer is used to transcribe a set of untranscribed data. Using this poorly transcribed data, correctly recognized portions are extracted based on a word confidence threshold. The …
-
Reconstructing Cell Lineage Trees from Phenotypic Features with Metric Learning
… explored supervised, weakly supervised, and unsupervised training settings. We present a cell lineage reconstruction benchmark, \emph{CellTreeBench}, to facilitate a comprehensive evaluation of our learning method. We benchmarked the method on (1) synthetic data modeled via Brownian motion …
-
Υβριδικό πιθανοτικό δίκτυο μη επιβλεπόμενης μάθησης για την ανάλυση ακολουθιών συμβόλων και βιολογικών αλληλουχιών
… learning networks can be formed by merging unsupervisedlearning/self-organizing techniques and probabilistic approaches, in an effort tocombine their advantages and overcome certain of their limitations. The present PhDthesis introduces such a hybrid approach that combines the …
-
Modeling Pedestrian Behavior in Video
… algorithms. The method we have developed for training such a pedestrian model operates by optimizing a set of weights governing an aggregate energy function in order to minimize a loss function computed between a model's prediction and annotated ground-truth pedestrian tracks. The formulation …
-
Neural Network Approaches to 2D Acoustic Wave Modelling for Room Acoustics Simulation
… The limitations of the PINN architecture and unsupervised training are explored, leading to a Fourier Operator Network (FNO) and supervised training scheme solution. The FNO architecture is shown to solve for various 2D acoustic system parameters of increasing complexity without retraining, …
-
Time-domain Multi-channel Speech Separation for Overlapping Speech Recognition
… approach. The third contribution studies unsupervised and semi-supervised learning approaches to establish a separation system in situations where only a limited amount of clean data is accessible. An existing unsupervised training strategy that trains a separation system to predict …
-
Dynamic coordination training with mobile robotic feedback to improve neuromuscular response and engagement in joint movement and balance therapy
… programs focused on improving balance through training can mitigate fall risks, especially using an individualized approach with real-time biofeedback. However, compliance to standard rehabilitation routines is often poor because they require individuals to consistently perform repetitive, …
Page 1 of 2