English Chinese ad-hoc, ad hoc (fix/method) 特设的（修改/方法） training (dataset) 训练（集） n. evaluation (dataset) 验证（集） n. testing (dataset) 测试（集） n. train 训练 v. evaluate 验证 v. test 测试 v. 试 v.
“if you plan to use deep learning extensively (>150 hrs/mo), building your own deep learning workstation might be the right move.” [medium] Baidu AI Studio (only for PaddlePaddle) Paperspace (cooperating with fast.ai) Google Colab (cooperating with fast.ai) vast.ai (C2C/P2P sharing, very cheap, a lot of time to init/load/unload) Kaggle (max 6h, good GPU but complex steps to use) MS Azure Amazon FloydHub (special CLI interface) ref: CN intro: Paperspace vs. Colab, 2019 Best Deals in Deep Learning Cloud Providers, 2018 比较云GPU平台
德州农工大学开源RLCard：帮你快速训练会斗地主的智能体 See simple DEF & code in 邱锡鹏 教授 2020 神经网络与深度学习.
See also: Machine Learning - Just-do-it (hands on) Basics Math Books Favoured # MLY (Andrew Ng), Machine Learning Yearning (EN full: ch1-13), 《CN: 机器学习秘籍》(CN Web online), (CN Github) and someone’s notes: part 1 (bak), part 2 (bak) and part 3. MLAPP (Kevin Murphy), Machine Learning - A Probablistic Perspective, is more comprehensive, insightful and interesting, and contains more “real” examples/problems. However, the presents are kinda out of order, which can be difficult to follow for a first book. ...
See also: DL-theory > ## cnn visualization/comprehensibility 可解释的机器学习 (What) 可解释性的重要性 (Why) 具体如何解释 (How) Insights which can be extracted from the models Permutation Importance Partial Dependency Plots SHAP Values SHAP Values in Advance LIME (万金油), Tree interpreter, etc. 凭什么相信你，我的CNN模型？关于CNN模型可解释性的思考 inc.:CAM, Grad-CAM, Lime. Book by Christoph Molnar: Interpretable Machine Learning – A Guide for Making Black Box Models Explainable (GitHub), (CN) All-in-one: SHAP. ref: https://medium.com/@Zelros/a-brief-history-of-machine-learning-models-explainability-f1c3301be9dc Causality / Causal Inference # Jonas Peters, Dominik Janzing and Bernhard Schölkopf 2017 - Elements of Causal Inference ; Bernhard Schölkopf 2019 - Causality for Machine Learning, ...
See also: ML books. This blog collects some useful materials for non-theory learners like engineers. Book: python-machine-learning-book code on github ML from scratch (py) Erik Linder-Norén, Stockholm Machine learning, in numpy (so, also scratch, but a lot Neural Nets & RL) David Bourgin, CA 7 Types of Regression Techniques you should know (modern regressions) analyticsvidhya evernote backup GitHub标星1.3k！一款功能强大的特征选择工具 2019.11 Causality analysis: MS dowhy, Causalinference in py (inactive), CausalInference in Julia, IBM causallib etc. ...
This is a summary of KD-nuggets blogs: here and here. Pictures are modified for my own notes. Tools Associations # sunny’s conclusion # Possible framework 1: Hadoop + Spark + Python + scikit. Possible framework 2: SQL+ Excel + Tableau. Try NOT use: RapidMiner, KNIME (whatever situation). Big Data Related Tools # Deep Learning Related Tools # Big_Data- / Deep_Learning-Related Tools # Conclusion 1: Big_Data & DL are positively related. ...