Search Results for author: Alvin Chan

Found 21 papers, 9 papers with code

A Survey on AI Sustainability: Emerging Trends on Learning Algorithms and Research Challenges

no code implementations8 May 2022 Zhenghua Chen, Min Wu, Alvin Chan, XiaoLi Li, Yew-Soon Ong

We believe that this technical review can help to promote a sustainable development of AI R&D activities for the research community.

Fairness

FastTrees: Parallel Latent Tree-Induction for Faster Sequence Encoding

1 code implementation28 Nov 2021 Bill Tuck Weng Pung, Alvin Chan

Moreover, we show that the FASTTREES module can be applied to enhance Transformer models, achieving performance gains on three sequence transduction tasks (machine translation, subject-verb agreement and mathematical language understanding), paving the way for modular tree induction modules.

Language Modelling Machine Translation +2

ORCHARD: A Benchmark For Measuring Systematic Generalization of Multi-Hierarchical Reasoning

1 code implementation28 Nov 2021 Bill Tuck Weng Pung, Alvin Chan

The ability to reason with multiple hierarchical structures is an attractive and desirable property of sequential inductive biases for natural language processing.

ListOps Relational Reasoning +1

Deep Extrapolation for Attribute-Enhanced Generation

1 code implementation NeurIPS 2021 Alvin Chan, Ali Madani, Ben Krause, Nikhil Naik

Attribute extrapolation in sample generation is challenging for deep neural networks operating beyond the training distribution.

Attribute

RNA Alternative Splicing Prediction with Discrete Compositional Energy Network

2 code implementations7 Mar 2021 Alvin Chan, Anna Korsakova, Yew-Soon Ong, Fernaldo Richtia Winnerdy, Kah Wai Lim, Anh Tuan Phan

In the case of alternative splicing prediction, DCEN models mRNA transcript probabilities through its constituent splice junctions' energy values.

Player Identification in Hockey Broadcast Videos

no code implementations5 Sep 2020 Alvin Chan, Martin D. Levine, Mehrsan Javan

We propose an end-to-end trainable ResNet+LSTM network, with a residual network (ResNet) base and a long short-term memory (LSTM) layer, to discover spatio-temporal features of jersey numbers over time and learn long-term dependencies.

CoCon: A Self-Supervised Approach for Controlled Text Generation

1 code implementation ICLR 2021 Alvin Chan, Yew-Soon Ong, Bill Pung, Aston Zhang, Jie Fu

While there are studies that seek to control high-level attributes (such as sentiment and topic) of generated text, there is still a lack of more precise control over its content at the word- and phrase-level.

Text Generation

Jacobian Adversarially Regularized Networks for Robustness

1 code implementation ICLR 2020 Alvin Chan, Yi Tay, Yew Soon Ong, Jie Fu

Adversarial examples are crafted with imperceptible perturbations with the intent to fool neural networks.

What it Thinks is Important is Important: Robustness Transfers through Input Gradients

2 code implementations CVPR 2020 Alvin Chan, Yi Tay, Yew-Soon Ong

Learned weights of models robust to such perturbations are previously found to be transferable across different tasks but this applies only if the model architecture for the source and target tasks is the same.

Adversarial Robustness

Poison as a Cure: Detecting & Neutralizing Variable-Sized Backdoor Attacks in Deep Neural Networks

no code implementations19 Nov 2019 Alvin Chan, Yew-Soon Ong

Existing defenses are effective under certain conditions such as a small size of the poison pattern, knowledge about the ratio of poisoned training samples or when a validated clean dataset is available.

Metamorphic Relation Based Adversarial Attacks on Differentiable Neural Computer

no code implementations7 Sep 2018 Alvin Chan, Lei Ma, Felix Juefei-Xu, Xiaofei Xie, Yang Liu, Yew Soon Ong

Deep neural networks (DNN), while becoming the driving force of many novel technology and achieving tremendous success in many cutting-edge applications, are still vulnerable to adversarial attacks.

Question Answering Relation

Cannot find the paper you are looking for? You can Submit a new open access paper.