Design of self-organizing fuzzy neural networks using evolutionary algorithms by Fan, Lihua

“…However, it has two weaknesses: (1) it needs sufficient training data to train the network to obtain a satisfactory modelling result; (2) the modelling will fail if a set of linearly-spacing training data is present to the data. …”
Get full text

Virtual palpation by Luo, Ting.

“…This Virtual Palpation Tool can help to train interns to learn how to palpate abdomen and feel the organs beneath the skin surface. …”
Get full text

Virtual reality on vision improvement by Yu, Haitao

“…Founded that although eye exercise may not cure nearsightedness totally, it is a good way to train you eye by increasing eye function to focus better and reducing eye stress. …”
Get full text

Machine learning driven synthesis of two-dimensional materials by Chia, Jia Jun

“…In this study, we aim to make use of machine learning, specifically the Decision Tree Learning approach to train on a set of data of Molybdenum Disulfide (MoS2) obtained from Chemical Vapor Deposition (CVD) to predict the optimum conditions for the growth of such material. …”
Get full text

Home security system based on face recognition techniques by Yuan, Wanheng

“…The first one is using a pre-trained network to embed and recognize face of my dataset. …”
Get full text

Using Principles from Cognitive Science to Analyze and Guide Language-Related Neural Networks by Tucker, Mycal

“…In my second branch of work, rather than training neural agents from scratch, I probe pre-trained language models and found that some use representations of syntax in making predictions. …”
Get full text

Multi-path region mining for weakly supervised 3D semantic segmentation on point clouds by Wei, Jiacheng, Lin, Guosheng, Yap, Kim-Hui, Hung, Tzu-Yi, Xie, Lihua

“…Then, we use the point-level pseudo label to train a point cloud segmentation network in a fully supervised manner. …”
Get full text

On the Power of Decision Trees in Auto-Regressive Language Modeling by Gan, Yulu, Galanti, Tomer, Poggio, Tomaso, Malach, Eran

“…Our analysis provides bounds on the size, depth, and computational efficiency of ARDTs, highlighting their surprising computational power. Empirically, we train ARDTs on simple language generation tasks, showing that they can learn to generate coherent and grammatically correct text on par with a smaller Transformer model. …”
Get full text

Semantic mapping for articulated objects by Luar, Shui Song

“…In this project, our main contributions are to re-train a semantic segmentation network on a smaller subset of items which can be considered prismatic or revolute. …”
Get full text

Facial spoofing indicator using deep learning by Lim, Eugen Wei Jie

“…Photo attack datasets were used to train the model and to test its accuracy by classifying 2 classes of images into fake and real. …”
Get full text

An AI powered nutrition information mobile application by Kwa, Daniel Shen Jun

“…Android Studio with Flutter Software Develop Kit (SDK) will be used to develop the mobile application and Python will be used to train AI models using both TensorFlow Lite and Google Colab.…”
Get full text

Encoder-decoder model for multistep prediction of lithium-ion battery state of health (SOH) by Ng, Qian Hui

“…Using experimental results to train and test the BiLSTM model, it can predict the SOH of lithium-ion batteries with high accuracy, making it a promising tool for predicting the remaining useful life (RUL) of batteries in real-world applications such as electric vehicles and renewable energy systems.…”
Get full text

MemeWar 2 : game platform for artificial intelligence research by Teo, Joyce Mei Li

“…MemeWar is a free-to-download and play 3D multi-agent simulation game that allows user to train an agent to fight against others in a battle. …”
Get full text

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

“…We utilize EEG recordings from 9 patients with epilepsy as training data to train various support vector machines (SVMs), and to build the cascades based on this SVMs. …”
Get full text

Euthanasia among quadriplegics: a containment of autonomy in disability cinema by Cheang, Wai Yee

“…Me Before You is the latest incarnation in a train of disability films whereby a quadriplegic character opts for euthanasia, and subsequently prevails in his or her decision. …”
Get full text

Ultrawide band-based navigation for multi-agents by Seah, Ryan Meng Yong

“…A total of two experiments were conducted to train the neural network. One of the neural networks used two micro-UAV in the training process while the other used three micro-UAV. …”
Get full text

Design of machine learning based face recognition system by Yeo, Alvin Jin Kuang

“…These faceprints of many different people in a dataset will be trained through machine learning and it will learn how to recognize faces in that dataset. …”
Get full text

Robotic navigation and obstacle avoidance with computer vision and deep learning by Heng, Shaun Wei Quan

“…To train the image classification CNN, data was gathered. …”
Get full text

Building energy management system by Wee, Herman Ding Xian

“…The designed BEMS will perform modeling on a series of trained data for prediction and real-time forecast. …”
Get full text

Identifying individuals in video by combining 'generative' and discriminative head models by Everingham, M, Zisserman, A

“…Images rendered using the head model are used to train a discriminative tree-structured classifier giving efficient detection and pose estimates over a very wide pose range with three degrees of freedom. …”