2 code implementations • 30 Dec 2021 • Erico Tjoa, Hong Jing Khok, Tushar Chouhan, Guan Cuntai
This paper quantifies the quality of heatmap-based eXplainable AI (XAI) methods w. r. t image classification problem.
1 code implementation • 30 Dec 2021 • Erico Tjoa, Guan Cuntai
This paper proposes a way to circumvent the issues through the bottom-up design of neural networks with detailed interpretability, where each neuron or layer has its own meaning and utility that corresponds to humanly understandable concept.
2 code implementations • 30 Dec 2021 • Erico Tjoa, Guan Cuntai
This paper proposes two bottom-up interpretable neural network (NN) constructions for universal approximation, namely Triangularly-constructed NN (TNN) and Semi-Quantized Activation NN (SQANN).
no code implementations • 4 Apr 2021 • Erico Tjoa
This brief paper reports the shortcoming of a variant of convolutional neural network whose components are developed based on the pattern theory framework.
no code implementations • 5 Feb 2021 • Erico Tjoa, Guan Cuntai
Ongoing efforts to understand deep neural networks (DNN) have provided many insights, but DNNs remain incompletely understood.
Explainable artificial intelligence Explainable Artificial Intelligence (XAI) +1
2 code implementations • 7 Sep 2020 • Erico Tjoa, Cuntai Guan
Heatmaps can be appealing due to the intuitive and visual ways to understand them but assessing their qualities might not be straightforward.
Explainable artificial intelligence Explainable Artificial Intelligence (XAI)
2 code implementations • 5 Sep 2020 • Erico Tjoa, Guan Cuntai
The practical application of deep neural networks are still limited by their lack of transparency.
1 code implementation • 19 Nov 2019 • Erico Tjoa, Guo Heng, Lu Yuhao, Cuntai Guan
We implement a visual interpretability method Layer-wise Relevance Propagation (LRP) on top of 3D U-Net trained to perform lesion segmentation on the small dataset of multi-modal images provided by ISLES 2017 competition.
no code implementations • 17 Jul 2019 • Erico Tjoa, Cuntai Guan
Unfortunately, the blackbox nature of the deep learning is still unresolved, and many machine decisions are still poorly understood.
Explainable artificial intelligence Explainable Artificial Intelligence (XAI)