Интерпретируемое машинное обучение (2022) - История изменений

Irtery: /* Задания */

2022-04-30T11:03:49Z

Задания

← Предыдущая версия		Версия от 11:03, 30 апреля 2022
Строка 22:		Строка 22:
	== Задания ==		== Задания ==
	# Реализация LIME и SHAP [https://t.me/c/1554651430/20 Описание задания] Дедлайн: 26 марта		# Реализация LIME и SHAP [https://t.me/c/1554651430/20 Описание задания] Дедлайн: 26 марта
	# Интерпретация нейронных сетей для картинок [https://t.me/c/1554651430/78 Распределение методов интерпретации по людям] Дедлайн: 13 мая		# Интерпретация нейронных сетей для картинок [https://t.me/c/1554651430/78 Распределение методов интерпретации по людям] Дедлайн: 20 мая

	== Полезные ссылки и литература ==		== Полезные ссылки и литература ==

Irtery: /* Лекции */

2022-04-30T11:03:24Z

Лекции

← Предыдущая версия		Версия от 11:03, 30 апреля 2022
Строка 17:		Строка 17:
	* ''' 7.04''' - Saliency maps, DeconvNet, Occlusion Sensitivity, Integrated gradients [https://www.dropbox.com/s/db2c6y4xaccuhpw/6_SDOI.ipynb?dl=0 тетрадка] [https://www.dropbox.com/s/fq6p6vjeswrs08p/6_SDOI.mp4?dl=0 видео]		* ''' 7.04''' - Saliency maps, DeconvNet, Occlusion Sensitivity, Integrated gradients [https://www.dropbox.com/s/db2c6y4xaccuhpw/6_SDOI.ipynb?dl=0 тетрадка] [https://www.dropbox.com/s/fq6p6vjeswrs08p/6_SDOI.mp4?dl=0 видео]
	* '''14.04''' - Backpropagation methods: Vanila backprop, Guided backprop, CAM (class activation methods), Grad-CAM+, Grad-CAM++ [https://www.dropbox.com/s/hyk5dollr4d7iik/7_Backprop_methods.ipynb?dl=0 тетрадка]		* '''14.04''' - Backpropagation methods: Vanila backprop, Guided backprop, CAM (class activation methods), Grad-CAM+, Grad-CAM++ [https://www.dropbox.com/s/hyk5dollr4d7iik/7_Backprop_methods.ipynb?dl=0 тетрадка]
	* '''21.04''' - Visual Transformers [https://www.dropbox.com/s/~~x1kx7kzlzxq0otb~~/~~8_ViTs~~.~~mp4~~?dl=0 ~~видео~~] [https://www.dropbox.com/s/~~gfyb3g4y6epikxt~~/~~8_ViT~~.~~ipynb~~?dl=0 ~~тетрадка~~]		* '''21.04''' - Visual Transformers [https://www.dropbox.com/s/gfyb3g4y6epikxt/8_ViT.ipynb?dl=0 тетрадка] [https://www.dropbox.com/s/x1kx7kzlzxq0otb/8_ViTs.mp4?dl=0 видео]
	* '''28.04''' - Deep Taylor decomposition, Layer-wise Relevance Propagation [https://www.dropbox.com/s/~~28fod9sjccvgpdm~~/9_LRP.~~mp4~~?dl=0 ~~видео~~] [https://www.dropbox.com/s/~~n2ho4s8nfk2fpn6~~/9_LRP.~~ipynb~~?dl=0 ~~тетрадка~~]		* '''28.04''' - Deep Taylor decomposition, Layer-wise Relevance Propagation [https://www.dropbox.com/s/n2ho4s8nfk2fpn6/9_LRP.ipynb?dl=0 тетрадка] [https://www.dropbox.com/s/28fod9sjccvgpdm/9_LRP.mp4?dl=0 видео]

	== Задания ==		== Задания ==

Irtery: /* Лекции */

2022-04-30T11:02:56Z

Лекции

← Предыдущая версия		Версия от 11:02, 30 апреля 2022
Строка 17:		Строка 17:
	* ''' 7.04''' - Saliency maps, DeconvNet, Occlusion Sensitivity, Integrated gradients [https://www.dropbox.com/s/db2c6y4xaccuhpw/6_SDOI.ipynb?dl=0 тетрадка] [https://www.dropbox.com/s/fq6p6vjeswrs08p/6_SDOI.mp4?dl=0 видео]		* ''' 7.04''' - Saliency maps, DeconvNet, Occlusion Sensitivity, Integrated gradients [https://www.dropbox.com/s/db2c6y4xaccuhpw/6_SDOI.ipynb?dl=0 тетрадка] [https://www.dropbox.com/s/fq6p6vjeswrs08p/6_SDOI.mp4?dl=0 видео]
	* '''14.04''' - Backpropagation methods: Vanila backprop, Guided backprop, CAM (class activation methods), Grad-CAM+, Grad-CAM++ [https://www.dropbox.com/s/hyk5dollr4d7iik/7_Backprop_methods.ipynb?dl=0 тетрадка]		* '''14.04''' - Backpropagation methods: Vanila backprop, Guided backprop, CAM (class activation methods), Grad-CAM+, Grad-CAM++ [https://www.dropbox.com/s/hyk5dollr4d7iik/7_Backprop_methods.ipynb?dl=0 тетрадка]
	* '''21.04''' - Visual Transformers [https://www.dropbox.com/s/x1kx7kzlzxq0otb/8_ViTs.mp4?dl=0 видео][https://www.dropbox.com/s/gfyb3g4y6epikxt/8_ViT.ipynb?dl=0 тетрадка]		* '''21.04''' - Visual Transformers [https://www.dropbox.com/s/x1kx7kzlzxq0otb/8_ViTs.mp4?dl=0 видео] [https://www.dropbox.com/s/gfyb3g4y6epikxt/8_ViT.ipynb?dl=0 тетрадка]
	* '''28.04''' - Deep Taylor decomposition, Layer-wise Relevance Propagation [https://www.dropbox.com/s/28fod9sjccvgpdm/9_LRP.mp4?dl=0 видео][https://www.dropbox.com/s/n2ho4s8nfk2fpn6/9_LRP.ipynb?dl=0 тетрадка]		* '''28.04''' - Deep Taylor decomposition, Layer-wise Relevance Propagation [https://www.dropbox.com/s/28fod9sjccvgpdm/9_LRP.mp4?dl=0 видео] [https://www.dropbox.com/s/n2ho4s8nfk2fpn6/9_LRP.ipynb?dl=0 тетрадка]

	== Задания ==		== Задания ==

Irtery: /* Лекции */

2022-04-30T11:02:38Z

Лекции

← Предыдущая версия		Версия от 11:02, 30 апреля 2022
Строка 17:		Строка 17:
	* ''' 7.04''' - Saliency maps, DeconvNet, Occlusion Sensitivity, Integrated gradients [https://www.dropbox.com/s/db2c6y4xaccuhpw/6_SDOI.ipynb?dl=0 тетрадка] [https://www.dropbox.com/s/fq6p6vjeswrs08p/6_SDOI.mp4?dl=0 видео]		* ''' 7.04''' - Saliency maps, DeconvNet, Occlusion Sensitivity, Integrated gradients [https://www.dropbox.com/s/db2c6y4xaccuhpw/6_SDOI.ipynb?dl=0 тетрадка] [https://www.dropbox.com/s/fq6p6vjeswrs08p/6_SDOI.mp4?dl=0 видео]
	* '''14.04''' - Backpropagation methods: Vanila backprop, Guided backprop, CAM (class activation methods), Grad-CAM+, Grad-CAM++ [https://www.dropbox.com/s/hyk5dollr4d7iik/7_Backprop_methods.ipynb?dl=0 тетрадка]		* '''14.04''' - Backpropagation methods: Vanila backprop, Guided backprop, CAM (class activation methods), Grad-CAM+, Grad-CAM++ [https://www.dropbox.com/s/hyk5dollr4d7iik/7_Backprop_methods.ipynb?dl=0 тетрадка]
	* '''21.04''' - Visual Transformers [https://www.dropbox.com/s/x1kx7kzlzxq0otb/8_ViTs.mp4?dl=0 видео]		* '''21.04''' - Visual Transformers [https://www.dropbox.com/s/x1kx7kzlzxq0otb/8_ViTs.mp4?dl=0 видео][https://www.dropbox.com/s/gfyb3g4y6epikxt/8_ViT.ipynb?dl=0 тетрадка]
			* '''28.04''' - Deep Taylor decomposition, Layer-wise Relevance Propagation [https://www.dropbox.com/s/28fod9sjccvgpdm/9_LRP.mp4?dl=0 видео][https://www.dropbox.com/s/n2ho4s8nfk2fpn6/9_LRP.ipynb?dl=0 тетрадка]

	== Задания ==		== Задания ==

Irtery: /* Задания */

2022-04-21T13:07:47Z

Задания

← Предыдущая версия		Версия от 13:07, 21 апреля 2022
Строка 21:		Строка 21:
	== Задания ==		== Задания ==
	# Реализация LIME и SHAP [https://t.me/c/1554651430/20 Описание задания] Дедлайн: 26 марта		# Реализация LIME и SHAP [https://t.me/c/1554651430/20 Описание задания] Дедлайн: 26 марта
	# Интерпретация нейронных сетей для картинок [https://t.me/c/1554651430/78 Распределение методов интерпретации по людям] Дедлайн: 12 мая		# Интерпретация нейронных сетей для картинок [https://t.me/c/1554651430/78 Распределение методов интерпретации по людям] Дедлайн: 13 мая

	== Полезные ссылки и литература ==		== Полезные ссылки и литература ==

Irtery: /* Лекции */

2022-04-21T13:07:28Z

Лекции

← Предыдущая версия		Версия от 13:07, 21 апреля 2022
Строка 17:		Строка 17:
	* ''' 7.04''' - Saliency maps, DeconvNet, Occlusion Sensitivity, Integrated gradients [https://www.dropbox.com/s/db2c6y4xaccuhpw/6_SDOI.ipynb?dl=0 тетрадка] [https://www.dropbox.com/s/fq6p6vjeswrs08p/6_SDOI.mp4?dl=0 видео]		* ''' 7.04''' - Saliency maps, DeconvNet, Occlusion Sensitivity, Integrated gradients [https://www.dropbox.com/s/db2c6y4xaccuhpw/6_SDOI.ipynb?dl=0 тетрадка] [https://www.dropbox.com/s/fq6p6vjeswrs08p/6_SDOI.mp4?dl=0 видео]
	* '''14.04''' - Backpropagation methods: Vanila backprop, Guided backprop, CAM (class activation methods), Grad-CAM+, Grad-CAM++ [https://www.dropbox.com/s/hyk5dollr4d7iik/7_Backprop_methods.ipynb?dl=0 тетрадка]		* '''14.04''' - Backpropagation methods: Vanila backprop, Guided backprop, CAM (class activation methods), Grad-CAM+, Grad-CAM++ [https://www.dropbox.com/s/hyk5dollr4d7iik/7_Backprop_methods.ipynb?dl=0 тетрадка]
	* '''21.04''' - ~~ViT~~		* '''21.04''' - Visual Transformers [https://www.dropbox.com/s/x1kx7kzlzxq0otb/8_ViTs.mp4?dl=0 видео]

	== Задания ==		== Задания ==

Irtery: /* Лекции */

2022-04-21T12:50:59Z

Лекции

← Предыдущая версия		Версия от 12:50, 21 апреля 2022
Строка 17:		Строка 17:
	* ''' 7.04''' - Saliency maps, DeconvNet, Occlusion Sensitivity, Integrated gradients [https://www.dropbox.com/s/db2c6y4xaccuhpw/6_SDOI.ipynb?dl=0 тетрадка] [https://www.dropbox.com/s/fq6p6vjeswrs08p/6_SDOI.mp4?dl=0 видео]		* ''' 7.04''' - Saliency maps, DeconvNet, Occlusion Sensitivity, Integrated gradients [https://www.dropbox.com/s/db2c6y4xaccuhpw/6_SDOI.ipynb?dl=0 тетрадка] [https://www.dropbox.com/s/fq6p6vjeswrs08p/6_SDOI.mp4?dl=0 видео]
	* '''14.04''' - Backpropagation methods: Vanila backprop, Guided backprop, CAM (class activation methods), Grad-CAM+, Grad-CAM++ [https://www.dropbox.com/s/hyk5dollr4d7iik/7_Backprop_methods.ipynb?dl=0 тетрадка]		* '''14.04''' - Backpropagation methods: Vanila backprop, Guided backprop, CAM (class activation methods), Grad-CAM+, Grad-CAM++ [https://www.dropbox.com/s/hyk5dollr4d7iik/7_Backprop_methods.ipynb?dl=0 тетрадка]
			* '''21.04''' - ViT

	== Задания ==		== Задания ==

Irtery: /* Полезные ссылки и литература */

2022-04-21T12:13:15Z

Полезные ссылки и литература

← Предыдущая версия		Версия от 12:13, 21 апреля 2022
Строка 23:		Строка 23:

	== Полезные ссылки и литература ==		== Полезные ссылки и литература ==
			=== Книги ===
	# [https://cset.georgetown.edu/publication/machine-learning-and-cybersecurity/ Machine Learning and Cybersecurity (2021)]		# [https://cset.georgetown.edu/publication/machine-learning-and-cybersecurity/ Machine Learning and Cybersecurity (2021)]
	# [https://www.dropbox.com/s/wd6g3jhi0qy3eyv/interpretable-machine-learning.pdf?dl=0 Molnar "Interpretable Machine Learning" (2020)]		# [https://www.dropbox.com/s/wd6g3jhi0qy3eyv/interpretable-machine-learning.pdf?dl=0 Molnar "Interpretable Machine Learning" (2020)]
	# [https://github.com/PacktPublishing/Interpretable-Machine-Learning-with-Python Masis "Interpretable Machine Learning with Python" (2021)]		# [https://github.com/PacktPublishing/Interpretable-Machine-Learning-with-Python Masis "Interpretable Machine Learning with Python" (2021)]
			# [https://www.dropbox.com/s/ive59hcn7783vpm/%D0%9B%D0%B5%D0%BA%D1%86%D0%B8%D0%B8_%D0%BF%D0%BE_%D1%84%D1%83%D0%BD%D0%BA%D1%86%D0%B8%D0%BE%D0%BD%D0%B0%D0%BB%D1%8C%D0%BD%D0%BE%D0%BC%D1%83_%D0%B0%D0%BD%D0%B0%D0%BB%D0%B8%D0%B7%D1%83_%D0%A5%D0%B5%D0%BB%D0%B5%D0%BC%D1%81%D0%BA%D0%B8%D0%B9_A_%D0%AF_z_lib_org.pdf?dl=0 Хелемский "Лекции по функциональному анализу"]
			=== Статьи ===
	# [https://www.dropbox.com/s/h7sa4zi3n44qmkb/lime_paper.pdf?dl=0 Ribeiro "“Why Should I Trust You?” Explaining the Predictions of Any Classifier" (2016)]		# [https://www.dropbox.com/s/h7sa4zi3n44qmkb/lime_paper.pdf?dl=0 Ribeiro "“Why Should I Trust You?” Explaining the Predictions of Any Classifier" (2016)]
			# Friedman, Jerome H. “Greedy function approximation: A gradient boosting machine.” Annals of statistics (2001): 1189-1232
			# Apley, Daniel W. “Visualizing the effects of predictor variables in black box supervised learning models.” arXiv preprint arXiv:1612.08468 (2016)
			# [https://arxiv.org/abs/1706.07979 "General Activation Maximization, Activation Maximization in Codespace, Simple Taylor Decomposition, Deep Taylor Decomposition, LRP-ab"]
			# [https://distill.pub/2017/feature-visualization/ "DeepDream"]
			# [https://arxiv.org/pdf/1312.6034.pdf "Saliency Map, Vanilla Backpropagation"]
			# [https://arxiv.org/pdf/1311.2901.pdf "DeConvNet Full Input Reconstruction, DeConvNet Partial Input Reconstruction, Occlusion Sensitivity"]
			# [https://arxiv.org/pdf/1412.6806.pdf "Guided Backpropagation"]
			# [https://arxiv.org/pdf/1703.01365.pdf "Integrated Gradients"]
			# [https://arxiv.org/pdf/1706.03825.pdf "SmoothGrad"]
			# [http://iphome.hhi.de/samek/pdf/MonXAI19.pdf "Deep Taylor Decomposition, LRP-0, -epsilon, -gamma, LRP-ab"]
			# [https://arxiv.org/pdf/1704.02685.pdf "DeepLIFT"]
			# [http://cnnlocalization.csail.mit.edu/Zhou_Learning_Deep_Features_CVPR_2016_paper.pdf "Class Activation Map (CAM)"]
			# [https://arxiv.org/pdf/1610.02391.pdf "Gradient-Weighted Class Activation Map (Grad-CAM)"]
			=== Репозитории и либы ===
	# https://github.com/marcotcr/lime		# https://github.com/marcotcr/lime
	# https://shap.readthedocs.io		# https://shap.readthedocs.io
	# https://scikit-learn.org/stable/modules/partial_dependence.html		# https://scikit-learn.org/stable/modules/partial_dependence.html
	~~# Friedman, Jerome H. “Greedy function approximation: A gradient boosting machine.” Annals of statistics (2001): 1189-1232~~
	~~# Apley, Daniel W. “Visualizing the effects of predictor variables in black box supervised learning models.” arXiv preprint arXiv:1612.08468 (2016)~~

Irtery: Add 14.04 lecture

2022-04-18T11:14:51Z

Add 14.04 lecture

← Предыдущая версия		Версия от 11:14, 18 апреля 2022
Строка 16:		Строка 16:
	* '''31.03''' - PDP, ICE, ALE [https://www.dropbox.com/s/ld05h4fh9zmo5l7/5_PDP_ICE_ALE.pdf?dl=0 слайды] [https://www.dropbox.com/s/fzxasn5m2zq9wcc/5_PDP_ICE_ALE.mp4?dl=0 видео]		* '''31.03''' - PDP, ICE, ALE [https://www.dropbox.com/s/ld05h4fh9zmo5l7/5_PDP_ICE_ALE.pdf?dl=0 слайды] [https://www.dropbox.com/s/fzxasn5m2zq9wcc/5_PDP_ICE_ALE.mp4?dl=0 видео]
	* ''' 7.04''' - Saliency maps, DeconvNet, Occlusion Sensitivity, Integrated gradients [https://www.dropbox.com/s/db2c6y4xaccuhpw/6_SDOI.ipynb?dl=0 тетрадка] [https://www.dropbox.com/s/fq6p6vjeswrs08p/6_SDOI.mp4?dl=0 видео]		* ''' 7.04''' - Saliency maps, DeconvNet, Occlusion Sensitivity, Integrated gradients [https://www.dropbox.com/s/db2c6y4xaccuhpw/6_SDOI.ipynb?dl=0 тетрадка] [https://www.dropbox.com/s/fq6p6vjeswrs08p/6_SDOI.mp4?dl=0 видео]
			* '''14.04''' - Backpropagation methods: Vanila backprop, Guided backprop, CAM (class activation methods), Grad-CAM+, Grad-CAM++ [https://www.dropbox.com/s/hyk5dollr4d7iik/7_Backprop_methods.ipynb?dl=0 тетрадка]

	== Задания ==		== Задания ==

Irtery: /* Задания */

2022-04-08T17:14:52Z

Задания

← Предыдущая версия		Версия от 17:14, 8 апреля 2022
Строка 19:		Строка 19:
	== Задания ==		== Задания ==
	# Реализация LIME и SHAP [https://t.me/c/1554651430/20 Описание задания] Дедлайн: 26 марта		# Реализация LIME и SHAP [https://t.me/c/1554651430/20 Описание задания] Дедлайн: 26 марта
	# Интерпретация нейронных сетей для картинок [https://t.me/c/1554651430/78 Распределение методов интерпретации по людям] Дедлайн: ~~конец апреля~~		# Интерпретация нейронных сетей для картинок [https://t.me/c/1554651430/78 Распределение методов интерпретации по людям] Дедлайн: 12 мая

	== Полезные ссылки и литература ==		== Полезные ссылки и литература ==