Variational maximization-maximization of Bayesian mixture models and application to unsupervised image classification od Lim, Kart-Leong

“...A recent image prior technique combine unsupervised learning with Markov Random Field (MRF) by replacing the MRF potential with an unsupervised learner. ...”
Polni tekst

Robust human motion prediction for safe and efficient human-robot interaction od Lasota, Przemyslaw A.(Przemyslaw Andrzej)

Polni tekst

Deep feature learning for image classification via countering over-fitting od Qing, Yuanyuan

“...Overall, this thesis discussed the over-fitting problem of deep learning-based feature learning in visual understanding from two perspectives : 1) Over-fitting problem of supervised learning due to network architecture. 2) Over-fitting problem in semi-supervised and unsupervised learning due to the lack of data annotation....”
Polni tekst

FPGA acceleration of continual learning at the edge od Piyasena Gane Pathirannahelage Duvindu

“...The SONN model performs unsupervised learning from embedding features extracted from the CNN model by dynamically growing neurons and connections. ...”
Polni tekst

Using deep learning for quality control in cyber-manufacturing od Dai, Wenting

“...Based on these two principles, unsupervised learning (including clustering and anomaly detection), and active learning are focused on in this thesis. ...”
Polni tekst

Advancement in graph data mining: applications in unsupervised, continual, and few-shot learning od Rakaraddi, Appan

“...We propose a method for graph data mining as a regression problem for the estimation of Eigenvector Centrality in graphs with a GNN based approach in a completely unsupervised learning environment. To achieve this, we define an Encoder-Decoder based model architecture called CUL. ...”
Polni tekst

Multi-modal optical microscopy image analysis and matching techniques for spatially encoded bead-based microarrays od Datta, Abhik

“...These methods are developed such that they require minimal parameter tuning, and are able to deal with noisy images acquired in uncontrolled environments As part of the bright and dark field image processing we have developed two novel methods: a fully automatic method for detecting the underlying micro-well grid structure in the images, and an unsupervised learning based method to classify the micro-wells as either empty or containing a bead. ...”
Polni tekst

Towards better prediction and content detection through online social media mining od Chen, Weiling

“...In order to detect the few but potentially harmful rumors to prevent the public issues they may cause, the author proposes an unsupervised learning model combining Recurrent Neural Networks (RNN) and Autoencoders (AE) to distinguish rumors as anomalies from other credible microblogs based on users' behaviors. ...”
Polni tekst

Light-evoked deformations in rod photoreceptors, pigment epithelium and subretinal space revealed by prolonged and multilayered optoretinography od Tan, Bingyao, Li, Huakun, Zhuo, Yueming, Han, Le, Mupparapu, Rajeshkumar, Nanni, Davide, Barathi, Veluchamy Amutha, Palanker, Daniel, Schmetterer, Leopold, Ling, Tong

“...Here, by employing a phase-restoring subpixel motion correction algorithm, which enables imaging of the nanometer-scale tissue dynamics during minute-long recordings, and unsupervised learning of spatiotemporal patterns, we discover optical signatures of the other retinal structures' response to visual stimuli. ...”
Polni tekst

Techniques for large scale deployment of demand-aware bus transit systems od Perera, Talagalage Thilina Dharshana

“...Experimental results confirm that, compared to a widely-used unsupervised learning algorithm, the zone-wise runtime has improved by 83% while also improving the quality of routes. ...”
Polni tekst

Machine learning based online traffic incident detection and management for urban networks od Yang, Huan

“...The other is a novel unsupervised learning based automatic incident detection (AID) method using traffic flow data collected by Inductive loop detectors (ILDs). ...”
Polni tekst

Utilizing electronic, ionic and photonic coupling for neuromorphic devices od John, Rohit Abraham

“...Network-level simulations of unsupervised learning of handwritten digit images utilizing experimentally-derived device parameters, validates the utility of these memristors for energy-efficient neuromorphic computations, paving way for novel ionotronic neuromorphic architectures with halide perovskites as the active material. ...”
Polni tekst
Polni tekst

Autonomous deep learning for continual learning in complex data stream environment od Ashfahani, Andri

“...Another important finding is that the combination of self-clustering mechanism and latent-based regularization delivers better accuracy compared to most baselines in dealing with unsupervised learning problems. Further, this mechanism successfully reduces the risk of catastrophic forgetting in continual learning environments. ...”
Polni tekst

Joint learning of motion estimation and segmentation for cardiac MR image sequences od Qin, C, Bai, W, Schlemper, J, Petersen, SE, Piechnik, SK, Neubauer, S, Rueckert, D

“...This enables the weakly-supervised segmentation by taking advantage of features that are unsupervisedly learned in the motion estimation branch from a large amount of unannotated data. ...”

Learning a probabilistic latent space of object shapes via 3D generative-adversarial modeling od Wu, Jiajun, Zhang, Chengkai, Xue, Tianfan, Freeman, William T., Tenenbaum, Joshua B.

“...Experiments demonstrate that our method generates high-quality 3D objects, and our unsupervisedly learned features achieve impressive performance on 3D object recognition, comparable with those of supervised learning methods....”
Polni tekst
Polni tekst
Polni tekst
Polni tekst
Polni tekst

Generative adversarial modeling of 3D shapes od Zhang, Chengkai, M. Eng. Massachusetts Institute of Technology

Polni tekst