Learning Bregman distance functions for semi-supervised clustering by Wu, Lei., Hoi, Steven C. H., Jin, Rong., Zhu, Jianke., Yu, Nenghai.

“…We verify the efficacy of the proposed distance learning method with extensive experiments on semi-supervised clustering. …”
Get full text
Get full text

Deep structured output learning for unconstrained text recognition by Jaderberg, M, Simonyan, K, Vedaldi, A, Zisserman, A

“…To test the generalisation of our model, we also perform experiments with random alpha-numeric strings to evaluate the method when no visual language model is applicable.…”

Learning progressive joint propagation for human motion prediction by Cai, Yujun, Huang, Lin, Wang, Yiwei, Cham, Tat-Jen, Cai, Jianfei, Yuan, Junsong, Liu, Jun, Yang, Xu, Zhu, Yiheng, Shen, Xiaohui, Liu, Ding, Liu, Jing, Thalmann, Nadia Magnenat

Get full text

A deep learning approach to image quality assessment by Feng, Yeli

“…Lastly, we present a method that helps diagnosis AI to recognize view types of chest radiographs.…”
Get full text
Get full text

Towards haptic intelligence in robots by learning from demonstration by Turlapati Sri Harsha

“…Another aspect of haptic intelligence is in the learning of contact tasks from human demonstrations. …”
Get full text

Prediction analysis of COVID-19 in Selangor by using backpropagation algorithm with conjugate gradient method by Ajmal Khan, Noor Amirah, Marjugi, Siti Mahani

“…The Fletcher-Reeves approach can improve the efficiency of the backpropagation algorithm by having a faster convergence rate than other methods such as the scaled conjugate gradient method. …”
Get full text

Robust Markov decision processes: a place where AI and formal methods meet by Suilen, M, Badings, T, Bovy, EM, Parker, D, Jansen, N

“…In particular, we discuss RMDP semantics and how to solve them by extending standard MDP methods such as value iteration and policy iteration. …”

A word-embedding-based steganalysis method for linguistic steganography via synonym substitution by Xiang, Lingyun, Yu, Jingmin, Yang, Chunfang, Zeng, Daojian, Shen, Xiaobo

“…In addition, the detection performance can be further improved by learning better word embeddings.…”
Get full text
Get full text

A data-driven method for automated data superposition with applications in soft matter science by Lennon, Kyle R., McKinley, Gareth H., Swan, James W.

“…In this work, we develop a data-driven, nonparametric method for superposing experimental data with arbitrary coordinate transformations, which employs Gaussian process regression to learn statistical models that describe the data, and then uses maximum a posteriori estimation to optimally superpose the data sets. …”
Get full text

Comprehensive analysis of feature extraction methods for emotion recognition from multichannel EEG recordings by Yuvaraj, Rajamanickam, Thagavel, Prasanth, Thomas, John, Fogarty, Jack, Ali, Farhan

“…Advances in signal processing and machine learning have expedited electroencephalogram (EEG)-based emotion recognition research, and numerous EEG signal features have been investigated to detect or characterize human emotions. …”
Get full text

Chemical methods in dewatering clayey slurry for land reclamation (GE27AB/ISP) by Andi

Get full text

Quantum computing and quantum neural networks: their foundation, optimisation, and application by Pointing, J

“…Our results suggest a bias-expressivity tradeoff, highlighting the need for alternative frameworks to make QNNs effective general-purpose learning tools for classical data. We explore the optimisation of quantum circuits by creating a new quantum compiler with a novel technique: we automatically generate quantum circuits that are equivalent and design a tiling method to optimise larger circuits according to a customisable cost function. …”

Methods of growth and transfer of carbon nanotubes onto substrates for advanced electrical and electronic applications by Ng, Zhi Kai

“…In this thesis, a water assisted CVD method for “self” delamination of VACNT from the growth substrate is proposed. …”
Get full text

Physics-informed machine learning for green data center operations by Wang, Ruihang

“…To expedite the adaptation with safety considerations, this thesis develops a physics-informed lifelong learning approach by supervising data collection with the previously identified transition model, fitting power usage and residual thermal models, pretraining the agent by interacting with these models, and deploying the agent for further fine-tuning. …”
Get full text

Additive quantization for truly tiny compressed diffusion models by Hasan, Adil

Get full text

Open world object detection: a survey by Li, Yiming, Wang, Yi, Wang, Wenqian, Lin, Dan, Li, Bingbing, Yap, Kim-Hui

“…This survey paper offers a thorough review of the OWOD domain, covering essential aspects, including problem definitions, benchmark datasets, source codes, evaluation metrics, and a comparative study of existing methods. Additionally, we investigate related areas like open set recognition (OSR) and incremental learning (IL), underlining their relevance to OWOD. …”
Get full text

Chemical analysis of silica doped hydroxyapatite biomaterials consolidated by a spark plasma sintering method by Xu, Jinling, Khor, Khiam Aik

Get full text
Get full text

Generalizability of deep neural networks for vertical cup-to-disc ratio estimation in ultra-widefield and amartphone-based fundus images by Yap, Boon Peng, Li, Kelvin Zhenghao, Toh, En Qi, Low, Kok Yao, Rani, Sumaya Khan, Goh, Eunice Jin Hui, Hui, Vivien Yip Cherng, Ng, Beng Koon, Lim, Tock Han

“…Purpose: To develop and validate a deep learning system (DLS) for estimation of vertical cup-to-disc ratio (vCDR) in ultra-widefield (UWF) and smartphone-based fundus images. …”
Get full text

Side channel attack on mobile devices using machine learning by Muhammad Jazeel Meerasah

“…These methods include methods that make use of a smartwatch and other means of attacks. …”
Get full text

A survey of few-shot learning for biomedical time series by Li, C, Denison, T, Zhu, T

“…This survey provides a comprehensive review and comparison of few-shot learning methods for biomedical time series applications. …”