A spiking neural network for pattern recognition by Nurin Atikah Bohari

Get full text

Robustness to training disturbances in SpikeProp Learning by Shrestha, Sumit Bam, Song, Qing

“…Stability is a key issue during spiking neural network training using SpikeProp. The inherent nonlinearity of Spiking Neuron means that the learning manifold changes abruptly; therefore, we need to carefully choose the learning steps at every instance. …”
Get full text

3D spine shape estimation from single 2D DXA by Bourigault, E, Jamaludin, A, Zisserman, A

“…Using these two orthogonal projections of the spine (coronal in DXA, and sagittal from the prediction), we are able to describe the 3D shape of the spine. …”

Frail Line by Er, Kia Hui, Ong, Grace Xi Wei, Ho, Baofei, Tan, Jit Quan, Boithar, Faizal

“…Frail Line is a story about the changed dynamics of a father-daughter relationship after a separation of many years. …”
Get full text

End of the line by Chia, Wei Ting

“…My Final Year Project “End of the Line” is an experimental effort to create an expressive piece of game design, writing and drawing to explore the possibilities of creating a narrative driven card game that combines elements of walking simulators, interactive fiction, and strategic card games. …”
Get full text

Impact of spike anneal on ultra shallow junction formation by Lai, Chung Woh

“…This report explains the need for ultra shallow junctions for modern day CMOS devices, how spike anneal can help achieve this, reviews the important parameters if this process and how these parameters affect the performances of the CMOS transistors.…”
Get full text

Automated spike detection using cascade of simple classifiers by Guo, Jingyao

“…The infinite variety of spike morphologies and the similarity of spikes to normal EEG and artifacts also make the detection of spikes difficult. …”
Get full text

Effect of recycled fine aggregates on concrete properties by Lau, Jing Xi.

“…In this project, the bulk of the experiment conducted is mainly based on the effects of recycled fine aggregates on the properties of hardened concrete. …”
Get full text

RF processing of ultra-fine bioceramic materials by Rajendra Kumar

“…This study investigates the radio-frequency plasma synthesis of ultra-fine bioceramic materials.…”
Get full text

Ethnoichthyology of the First Record of Spine Bahaba (Bahaba polykladiskos) from Muar, Johor, Malaysia by Ilham-Norhakim, Mohd Lokman, Mohd Faudzir, Najmuddin, Hidayah, Haris, Othman, Nursyuhada, Ramli, Ramli, Sariyati Nur Hartini, Sariyati Nur Hartini, Rasul Abdullah, Halim Muhammad, Abdullah-Fauzi, Abdullah-Fauzi, Akmal, Fawwazah, Abdul-Latiff, Muhammad Abu Bakar

“…The Spine Bahaba (Bahaba polykladiskos), locally known as 'Gelama Tirusan,' is a member of the Sciaenidae fish family that is distributed across Southeast Asia, reaching as far as North Australia. …”
Get full text

Place recognition using line-junction-lines in urban environments by Tang, Xiaoyu, Fu, Wenhao, Jiang, Muyun, Peng, Guohao, Wu, Zhenyu, Yue, Yufeng, Wang, Danwei

“…Bag- of-Words (BoW) -based approach is the most popular solution due to its efficiency and robustness. We propose to use Line- Junction-Line (LJL) to build a BoW for place recognition in urban environments. …”
Get full text

Designing a spiking neural network system for object recognition by Thong, Jing Yuan

“…Widely touted as the 3rd generation of neural networks, Spiking Neural Networks were introduced as an enhanced representation of working memory. …”
Get full text

Dissipative solitons with extreme spikes in the normal and anomalous dispersion regimes by Akhmediev, N., Soto-Crespo, J. M., Vouzas, Peter, Devine, N., Chang, Wonkeun

“…In this paper, one recent example is considered—dissipative solitons with extreme spikes (DSESs). It was found that DSESs exist in large regions of the parameter space of the complex cubic–quintic Ginzburg–Landau equation. …”
Get full text

Bayesian lesion estimation with a structured spike-and-slab prior by Menacher, A, Nichols, T, Holmes, C, Ganjgahi, H

“…Our method also accounts for underestimation of posterior variance due to variational inference by providing an approximate posterior sampling approach based on Bayesian bootstrap ideas and spike-and-slab priors with random shrinkage targets. …”

Somatosensory and clinical profiles of patients with spine-related and clinical framework-based neck–arm pain by Kapitza, C, Ballenberger, N, Luedtke, K, Schmid, AB, Tampin, B

“…<p>Spine-related neck–arm pain is heterogeneous and may present on a spectrum between nociceptive and neuropathic pain. …”

Investigating Interventions in Fine-grained Contexts for Habit Formation by Khan, Mina

“…Habits are automatic responses to specific contextual cues, and can help sustain behavior change. Fine-grained specific contexts are commonly used in habit formation, but interventions in automatically-detected fine-grained contexts have rarely been explored for habit formation. …”
Get full text

FPGA implementation of spiking convolutional neural networks for voice keyword recognition by Ng, Wei Soon

“…The spiking convolutional neural network (SCNN) is a hybrid model of both the spiking neural network (SNN) and convolutional neural network (CNN). …”
Get full text

Investigating Fine-Tuning of Language Models for Multiple-Choice Questions by Wang, Ivy A.

“…We specifically investigate training data properties related to positional bias in fine-tuned language model performance on correctly answering MCQs. …”
Get full text

Fabrication of fine features using digital light processing stereolithography by Chew, Ze Yong

“…Thus, this project was developed with the objectives to: 1. reduce production cost of Stereolithography by optimizing low end commercial Stereolithography system – ASIGA Freeform Pico 39 Plus such that it is able to print fine features 2. explore effective and convenient post processing step such that it is able to reduce material wastage and at the same time further shorten production lead time The parameter study conducted revealed that every layer thickness has a specific optimal exposure time such that the layers could be printed just fine, with minimal compromise of the internal features’ accuracy. …”
Get full text

Investigating fine-tuning of large language models for text summarisation by Khaliq, Usama, Patel, Preeti

“…The limited performance increase from the fine-tuned models was likely due to small datasets and medium-sized LLMs. …”
Get full text