5 papers
Transferring Domain Knowledge with an Adviser in Continuous Tasks
Rukshan Wijesinghe, Kasun Vithanage, Dumindu Tissera +3
Recent advances in Reinforcement Learning (RL) have surpassed human-level performance in many simulated environments. However, existing reinforcement learning techniques are incapa…
Feature-Dependent Cross-Connections in Multi-Path Neural Networks
Dumindu Tissera, Kasun Vithanage, Rukshan Wijesinghe +3
Learning a particular task from a dataset, samples in which originate from diverse contexts, is challenging, and usually addressed by deepening or widening standard neural networks…
Context-Aware Multipath Networks
Dumindu Tissera, Kumara Kahatapitiya, Rukshan Wijesinghe +2
Making a single network effectively address diverse contexts---learning the variations within a dataset or multiple datasets---is an intriguing step towards achieving generalized i…
Wavelet based edge feature enhancement for convolutional neural networks
D. D. N. De Silva, S. Fernando, I. T. S. Piyatilake +1
Convolutional neural networks are able to perform a hierarchical learning process starting with local features. However, a limited attention is paid to enhancing such elementary le…
On Optimizing Deep Convolutional Neural Networks by Evolutionary Computing
M. U. B. Dias, D. D. N. De Silva, S. Fernando
Optimization for deep networks is currently a very active area of research. As neural networks become deeper, the ability in manually optimizing the network becomes harder. Mini-ba…