Deep neural decision forest (NDF) achieved remarkable performance on various vision tasks via combining decision tree and deep representation learning. In this work, we first trace the decision-making process of this model and visualize saliency maps to understand which portion of the input influence it more for both classification and regression problems. We then apply NDF on a multi-task coordinate regression problem and demonstrate the distribution of routing probabilities, which is vital for interpreting NDF yet not shown for regression problems. The pre-trained model and code for visualization will be available at https://github.com/Nicholasli1995/VisualizingNDF
Opening the Black Box of Financial AI with CLEAR-Trade: A CLass-Enhanced Attentive Response Approach for Explaining and Visualizing Deep Learning-Driven Stock Market Prediction
University of Guelph(圭尔夫大学);CIFAR(加拿大高等研究院);Vector Institute(向量研究所);University of Waterloo(滑铁卢大学);Waterloo AI Institute(滑铁卢人工智能研究所)
Visualizing the Diversity of Representations Learned by Bayesian Neural Networks
Machine Learning Group(机器学习研究组);Technical University of Berlin(柏林工业大学);BIFOLD – Berlin Institute for the Foundations of Learning and Data(BIFOLD – 柏林学习与数据基础研究所);Understandable Machine Intelligence Lab(可理解机器智能实验室);Leibniz Institute for Agriculture and Bioeconomy (ATB)(莱布尼茨农业与生物经济研究所(ATB));RIKEN Center for AIP(理化学研究所人工智能创新中心)
Visualizing Convolutional Networks for MRI-based Diagnosis of Alzheimer's Disease
Charité – Universitätsmedizin Berlin(柏林夏里特医学院);Freie Universität Berlin(柏林自由大学);Humboldt-Universität zu Berlin(柏林洪堡大学);Berlin Institute of Health(柏林健康研究所);Bernstein Center for Computational Neuroscience(伯恩斯坦计算神经科学中心);Berlin Center for Advanced Neuroimaging(柏林高级神经影像中心);Technical University Berlin(柏林工业大学)
Predicting Patient Recovery or Mortality Using Deep Neural Decision Tree and Forest
University of Tehran(德黑兰大学);Tehran University of Medical Sciences(德黑兰医科大学);Isfahan University of Medical Sciences(伊斯法罕医科大学);Mashhad University of Medical Sciences(马什哈德医科大学)
Seeing the random forest through the decision trees. Supporting learning health systems from histopathology with machine learning models: Challenges and opportunities
McMaster University(麦克马斯特大学);Mayo Clinic(梅奥诊所);Escarpment Cancer Research Institute(埃斯卡普门特癌症研究所);William Osler Health System(威廉·奥斯勒医疗系统);Mount Sinai Hospital(西奈山医院);Lunenfeld-Tanenbaum Research Institute(卢嫩菲尔德-塔南鲍姆研究所)
3D Adapted Random Forest Vision (3DARFV) for Untangling Heterogeneous-Fabric Exceeding Deep Learning Semantic Segmentation Efficiency at the Utmost Accuracy