Unsupervised Learning for Generative Scene Editing and Motion by Fang, David S.

“…Unsupervised learning for images and videos is important for many applications in computer vision. …”
Get full text

Object recognition using deep learning features by Zhu, Daiqing

“…However, previous algorithms need to train classifier to rank proposal and learn from object class recognition datasets. That is time consuming since those classifiers need to be trained again when new object category comes and database grow. …”
Get full text

Differentiable Vector Graphics Rasterization for Editing and Learning by Li, Tzu-Mao, Lukac, Mike, Gharbi, Michael, Ragan-Kelley, Jonathan

“…We introduce a differentiable rasterizer that bridges the vector graphics and raster image domains, enabling powerful raster-based loss functions, optimization procedures, and machine learning techniques to edit and generate vector content. …”
Get full text

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

“…The performance of learning using this scheme has been compared with the prevailing methods for different benchmark data sets and the results show that this method has stable learning reflected by minimal surges during learning, higher success in training instances, and faster learning as well.…”
Get full text

Vehicle re-identification using machine learning by Tang, Lisha

“…Finally, we address this Re-ID issue as a multi-task problem and employ Homoscedastic Uncertainty Learning to automatically balance the loss weightings. …”
Get full text

An analytic end-to-end collaborative learning algorithm by Li, Sitan, Cheah, Chien Chern

“…However, most current deep learning methods are black-box approaches that are more focused on empirical studies. …”
Get full text
Get full text

Goal modelling for deep reinforcement learning agents by Leung, Jonathan, Shen, Zhiqi, Zeng, Zhiwei, Miao, Chunyan

“…The experiments demonstrate that our method is more sample efficient and can obtain higher average rewards than other related methods that incorporate prior human knowledge in similar ways.…”
Get full text

Intelligent diagnostic feedback in virtual learning environment by Guo, Ruisheng

“…This research compares and contrasts several methods in order to investigate the effective use of intelligent feedback towards modelling the stages of students’learning. …”
Get full text

Structured sparse representations for supervised and unsupervised learning by Zeng, Yijie

“…Specifically, a slice-based online convolutional dictionary learning (SOCDL) method is proposed for unsupervised image processing tasks such as image reconstruction and inpainting. …”
Get full text

Machine learning based retinal vessel detection by Li, Hongru

“…In this dissertation, We adopted the traditional CV method based on 2D-matched Filter and deep learning U-NET method, and achieved good segmentation effect. …”
Get full text

Learning epipolar geometry from image sequences by Wexler, Y, Fitzgibbon, AW, Zisserman, A

Layer-wise learning framework for deep networks by Yu, Haoyao

“…The case examples demonstrate a rational compromise regarding layer-wise trainability and precision while validating the applicability of the proposed layer-wise learning method to determine the optimal number of layers for real-world scenarios.…”
Get full text

Development of a learning system for robot control by Tan, Chee Wee

Get full text

Case-based reasoning library for flexible learning by Zhang, Chuan Yu

“…Case-based reasoning can be applied in learning contexts through the collection, building, and indexing of case libraries. …”
Get full text

Multi-class classification using deep learning by Cao, Haozhi

Get full text

An artificial sensory neuron with tactile perceptual learning by Wan, Changjin, Chen, Geng, Fu, Yangming, Wang, Ming, Matsuhisa, Naoji, Pan, Shaowu, Pan, Liang, Yang, Hui, Wan, Qing, Zhu, Liqiang, Chen, Xiaodong

“…Furthermore, the recognition error rate can be dramatically decreased from 44% to 0.4% by integrating with the machine learning method. This work represents a step toward the design and use of neuromorphic electronic skin with artificial intelligence for robotics and prosthetics.…”
Get full text

Multi-Agent Reinforcement Learning for Autonomous Robotics by Vincent, Caroline R.

“…This thesis explores the application of multi-agent reinforcement learning (MARL) to autonomous robotics by teaching a central controller to navigate multiple agents across various environments without collisions. …”
Get full text
Get full text

Towards ILP-based LTLf passive learning by Ielo, A, Law, M, Fionda, V, Ricca, F, De Giacomo, G, De Giacomo, G, Russo, A

“…Inferring a LTL_f formula from a set of example traces, also known as passive learning, is a challenging task for model-based techniques. …”

Optimal persistent monitoring using reinforcement learning by Hu, Litao

“…This project aims to implement Reinforcement Learning (RL) in the multiple targets monitoring simulation with a single agent. …”
Get full text

Structured learning of human interactions in TV shows by Patron-Perez, A, Marszalek, M, Reid, I, Zisserman, A

“…We show that inference can be carried out with polynomial complexity in the number of people, and describe an efficient algorithm for this. The method is evaluated on a new dataset comprising 300 video clips acquired from 23 different TV shows and on the benchmark UT--Interaction dataset.…”