Certification of continuous professional development for librarians in Singapore by Choy, Fatt Cheong.

“…Continuing training and professional development is of perennial concern in every profession. …”
Get full text
Get full text

Tree-based Data Replay for More Efficient LLM Continual Learning by Bailey, Brian

“…The results indicate that focused data replay maintains model performance and enhance training efficiency. Models trained under restrictive replay conditions—excluding data from parent nodes—achieved perplexity scores within 1.5% of the baseline and reduced training time by up to 20%. …”
Get full text

Effects of music attrition on English-Mandarin Chinese bilinguals’ lexical tone perception and production in a foreign language by Toh, Xin Ru

“…Furthermore, individuals with a greater extent of tone language experience and musical training do not show additional advantages.…”
Get full text

From public health to AI safety: improving machine learning approaches by collecting, selecting, or reducing the need for high-quality data by Brauner, J

“…We develop a method to automatically select the most useful data at any given point in training, enabling us to train neural networks in fewer steps, to higher accuracy, and with lower computational costs.…”

A Non‐Intrusive Machine Learning Framework for Debiasing Long‐Time Coarse Resolution Climate Simulations and Quantifying Rare Events Statistics by Barthel Sorensen, B., Charalampopoulos, A., Zhang, S., Harrop, B. E., Leung, L. R., Sapsis, T. P.

“…Previous efforts have attempted to train such operators using loss functions that match statistics. …”
Get full text

Gesture recognition using Hidden Markov models by Shubhashree Sangameswaran.

Get full text

Generative pretrained autoregressive transformer graph neural network applied to the analysis and discovery of novel proteins by Buehler, Markus J

“…While our model is trained to ultimately perform eight distinct tasks, with available datasets, it can be extended to solve additional problems. …”
Get full text

wav2sleep: a unified multi-modal approach to sleep stage classification from physiological signals by Carter, JF, Tarassenko, L

“…Existing approaches to this problem have typically used deep learning models designed and trained to operate on one or more specific input signals. …”

Interpreting learned feedback patterns in large language models by Marks, L, Abdullah, A, Neo, C, Arike, R, Krueger, D, Torr, P, Barez, F

“…Reinforcement learning from human feedback (RLHF) is widely used to train large language models (LLMs). However, it is unclear whether LLMs accurately learn the underlying preferences in human feedback data. …”

Non-parametric induction motor rotor flux estimator based on feed-forward neural network by Siti Nursyuhada, Mahsahirun, Nik Rumzi, Nik Idris, Zulkifli, Md. Yusof, Sutikno, Tole

“…All the data collection, training and testing process are fully performed in MATLAB/Simulink environment. …”
Get full text

Adaptive generative adversarial network (GAN) for small datasets by Liu, Chang

“…This model provides a training model under a small data set, which can help us better train the neural network and improve training efficiency…”
Get full text

Exploiting diffusion prior for real-world image super-resolution by Wang, Jianyi, Yue, Zongsheng, Zhou, Shangchen, Chan, Kelvin C. K., Loy, Chen Change

“…We present a novel approach to leverage prior knowledge encapsulated in pre-trained text-to-image diffusion models for blind super-resolution. …”
Get full text

Meta-reinforcement learning in quantitative trading by Wong, Wei Jie

“…Not only can Meta-RL lead to good generalization performance to a set of similar tasks (Finn, Abbeel, & Levine, 2017) (Nichol, Achiam, & Schulman, 2018), it also reduces the need to train each task from scratch, significantly reducing training time. …”
Get full text

Effects of data amount and variation in deep learning-based tuberculosis diagnosis in chest X-ray scans by Bhorkar, A, Gonzales, RA

“…We hypothesized that models trained on a greater amount and variety of data would perform better than those trained on less and invariable data. …”

Dataset Design for Building Models of Chemical Reactivity by Raghavan, Priyanka, Haas, Brittany C, Ruos, Madeline E, Schleinitz, Jules, Doyle, Abigail G, Reisman, Sarah E, Sigman, Matthew S, Coley, Connor W

“…Perhaps the most determining factor is the composition of the training data and whether it is sufficient to train a model that can make accurate predictions over the full domain of interest. …”
Get full text

Pattern classification of odour for electronic nose by Tong, Wee Chin.

“…With the understanding of data acquisition, several experiments have been carried out to familiarise the process and obtain the training data. With a strong training data and the understanding of PNN, a program is developed to perform the classification function. …”
Get full text

Video processing of ophthalmic image sequences by Ambarish, Sridhar Prakash

“…The SVM was trained to detect the different tools present in the surgery, thereby identifying the surgical task. …”
Get full text

Placing objects in context via inpainting for out-of-distribution segmentation by De Jorge, P, Volpi, R, Dokania, PK, Torr, PHS, Rogez, G

“…For example, we utilize it to augment Cityscapes samples by incorporating a subset of Pascal classes and demonstrate that models trained on such data achieve comparable performance to the Pascal-trained baseline. …”

Effect of positive-negative image ratio on the performance of pedestrian detection model by Yee, Lai Kok, Ken, Tan Lit, Choo, Hau Sim, Asako, Yutaka, Lee, Kee Quen, Kang, Hooi Siang, Gan, Yee Siang, Chuan, Zunliang, Tey, Wah Yen, Nor Azwadi, Che Sidik

“…This occurred when both SVM and a Medium neural network were utilized to train the model with a ratio of 1:2, utilizing a total of 3000 images for the training phase. …”
Get full text

Deep learning-based concrete image analysis and generalization capability by Qian, Hanjie

“…Since the training data and test data belong to different distributions, and directly applying a trained model can be highly risky. …”
Get full text