Cambios
En el instante 11 de octubre de 2025, 1:23:00 UTC,
-
Añadido recurso Improved training of deep convolutional networks via minimum-variance regularized adaptive sampling a Improved training of deep convolutional networks via minimum-variance regularized adaptive sampling
f | 1 | { | f | 1 | { |
2 | "author": "A Rojas-Dominguez, SI Valdez, M Ornelas-Rodriguez, M | 2 | "author": "A Rojas-Dominguez, SI Valdez, M Ornelas-Rodriguez, M | ||
3 | Carpio", | 3 | Carpio", | ||
4 | "author_email": null, | 4 | "author_email": null, | ||
5 | "creator_user_id": "a3da3ec9-3fd4-47a4-8d04-0a90b09614e0", | 5 | "creator_user_id": "a3da3ec9-3fd4-47a4-8d04-0a90b09614e0", | ||
6 | "extras": [ | 6 | "extras": [ | ||
7 | { | 7 | { | ||
8 | "key": "Publicaci\u00f3n", | 8 | "key": "Publicaci\u00f3n", | ||
9 | "value": "Otro" | 9 | "value": "Otro" | ||
10 | }, | 10 | }, | ||
11 | { | 11 | { | ||
12 | "key": "Tipo", | 12 | "key": "Tipo", | ||
13 | "value": "Publicaci\u00f3n" | 13 | "value": "Publicaci\u00f3n" | ||
14 | } | 14 | } | ||
15 | ], | 15 | ], | ||
16 | "groups": [ | 16 | "groups": [ | ||
17 | { | 17 | { | ||
18 | "description": "Este grupo integra las publicaciones | 18 | "description": "Este grupo integra las publicaciones | ||
19 | acad\u00e9micas derivadas de los proyectos de investigaci\u00f3n del | 19 | acad\u00e9micas derivadas de los proyectos de investigaci\u00f3n del | ||
20 | Observatorio Metropolitano CentroGeo. Incluye art\u00edculos | 20 | Observatorio Metropolitano CentroGeo. Incluye art\u00edculos | ||
21 | presentados en congresos nacionales e internacionales, manuscritos en | 21 | presentados en congresos nacionales e internacionales, manuscritos en | ||
22 | formato preprint, cap\u00edtulos de libro y trabajos publicados en | 22 | formato preprint, cap\u00edtulos de libro y trabajos publicados en | ||
23 | revistas cient\u00edficas especializadas. Estos materiales reflejan la | 23 | revistas cient\u00edficas especializadas. Estos materiales reflejan la | ||
24 | labor de investigaci\u00f3n, desarrollo metodol\u00f3gico y | 24 | labor de investigaci\u00f3n, desarrollo metodol\u00f3gico y | ||
25 | an\u00e1lisis territorial del observatorio, contribuyendo al avance | 25 | an\u00e1lisis territorial del observatorio, contribuyendo al avance | ||
26 | del conocimiento en temas urbanos, metropolitanos y geoespaciales.", | 26 | del conocimiento en temas urbanos, metropolitanos y geoespaciales.", | ||
27 | "display_name": "Publicaciones", | 27 | "display_name": "Publicaciones", | ||
28 | "id": "a15a6b77-ddf5-4594-acab-7e772938a5b0", | 28 | "id": "a15a6b77-ddf5-4594-acab-7e772938a5b0", | ||
29 | "image_display_url": "", | 29 | "image_display_url": "", | ||
30 | "name": "publicaciones", | 30 | "name": "publicaciones", | ||
31 | "title": "Publicaciones" | 31 | "title": "Publicaciones" | ||
32 | } | 32 | } | ||
33 | ], | 33 | ], | ||
34 | "id": "05827633-b5a8-4eca-b268-e47d7075f3ae", | 34 | "id": "05827633-b5a8-4eca-b268-e47d7075f3ae", | ||
35 | "isopen": false, | 35 | "isopen": false, | ||
36 | "license_id": null, | 36 | "license_id": null, | ||
37 | "license_title": null, | 37 | "license_title": null, | ||
38 | "maintainer": null, | 38 | "maintainer": null, | ||
39 | "maintainer_email": null, | 39 | "maintainer_email": null, | ||
40 | "metadata_created": "2025-10-11T01:22:59.503253", | 40 | "metadata_created": "2025-10-11T01:22:59.503253", | ||
n | 41 | "metadata_modified": "2025-10-11T01:22:59.503262", | n | 41 | "metadata_modified": "2025-10-11T01:22:59.980531", |
42 | "name": | 42 | "name": | ||
43 | utional-networks-via-minimum-variance-regularized-adapt-c88440c631a7", | 43 | utional-networks-via-minimum-variance-regularized-adapt-c88440c631a7", | ||
44 | "notes": "Artificial intelligence (AI) is currently being utilized | 44 | "notes": "Artificial intelligence (AI) is currently being utilized | ||
45 | in a wide range of sophisticated applications, but the outcomes of | 45 | in a wide range of sophisticated applications, but the outcomes of | ||
46 | many AI models are challenging to comprehend and trust due to their | 46 | many AI models are challenging to comprehend and trust due to their | ||
47 | black-box nature. Usually, it is essential to understand the reasoning | 47 | black-box nature. Usually, it is essential to understand the reasoning | ||
48 | behind an AI model's decision-making. Thus, the need for eXplainable | 48 | behind an AI model's decision-making. Thus, the need for eXplainable | ||
49 | AI (XAI) methods for improving trust in AI models has arisen. XAI has | 49 | AI (XAI) methods for improving trust in AI models has arisen. XAI has | ||
50 | become a popular research subject within the AI field in recent years. | 50 | become a popular research subject within the AI field in recent years. | ||
51 | Existing survey papers have tackled the concepts of XAI, its general | 51 | Existing survey papers have tackled the concepts of XAI, its general | ||
52 | terms, and post-hoc explainability methods but there have not been any | 52 | terms, and post-hoc explainability methods but there have not been any | ||
53 | reviews that have looked at the assessment methods, available tools, | 53 | reviews that have looked at the assessment methods, available tools, | ||
54 | XAI datasets, and other related aspects. Therefore, in this | 54 | XAI datasets, and other related aspects. Therefore, in this | ||
55 | comprehensive study, we provide readers with an overview of the | 55 | comprehensive study, we provide readers with an overview of the | ||
56 | current research and trends in this rapidly emerging area with a case | 56 | current research and trends in this rapidly emerging area with a case | ||
57 | study example. The study starts by explaining the background of XAI, | 57 | study example. The study starts by explaining the background of XAI, | ||
58 | common definitions, and summarizing recently proposed techniques in | 58 | common definitions, and summarizing recently proposed techniques in | ||
59 | XAI for supervised machine learning. The review divides XAI techniques | 59 | XAI for supervised machine learning. The review divides XAI techniques | ||
60 | into four axes using a hierarchical categorization system: (i) data | 60 | into four axes using a hierarchical categorization system: (i) data | ||
61 | explainability, (ii) model explainability, (iii) post-hoc | 61 | explainability, (ii) model explainability, (iii) post-hoc | ||
62 | explainability, and (iv) assessment of explanations. We also introduce | 62 | explainability, and (iv) assessment of explanations. We also introduce | ||
63 | available evaluation metrics as well as open-source packages and | 63 | available evaluation metrics as well as open-source packages and | ||
64 | datasets with future research directions. Then, the significance of | 64 | datasets with future research directions. Then, the significance of | ||
65 | explainability in terms of legal demands, user viewpoints, and | 65 | explainability in terms of legal demands, user viewpoints, and | ||
66 | application orientation is outlined, termed as XAI concerns. This | 66 | application orientation is outlined, termed as XAI concerns. This | ||
67 | paper advocates for tailoring explanation content to specific user | 67 | paper advocates for tailoring explanation content to specific user | ||
68 | types. An examination of XAI techniques and evaluation was conducted | 68 | types. An examination of XAI techniques and evaluation was conducted | ||
69 | by looking at 410 critical articles, published between January 2016 | 69 | by looking at 410 critical articles, published between January 2016 | ||
70 | and October 2022, in reputed journals and using a wide range of | 70 | and October 2022, in reputed journals and using a wide range of | ||
71 | research databases as a source of information. The article is aimed at | 71 | research databases as a source of information. The article is aimed at | ||
72 | XAI researchers who are interested in making their AI models more | 72 | XAI researchers who are interested in making their AI models more | ||
73 | trustworthy, as well as towards researchers from other disciplines who | 73 | trustworthy, as well as towards researchers from other disciplines who | ||
74 | are looking for effective XAI methods to complete tasks with | 74 | are looking for effective XAI methods to complete tasks with | ||
75 | confidence while communicating meaning from data.", | 75 | confidence while communicating meaning from data.", | ||
n | 76 | "num_resources": 0, | n | 76 | "num_resources": 1, |
77 | "num_tags": 3, | 77 | "num_tags": 3, | ||
78 | "organization": { | 78 | "organization": { | ||
79 | "approval_status": "approved", | 79 | "approval_status": "approved", | ||
80 | "created": "2022-05-19T00:10:30.480393", | 80 | "created": "2022-05-19T00:10:30.480393", | ||
81 | "description": "Observatorio Metropolitano CentroGeo", | 81 | "description": "Observatorio Metropolitano CentroGeo", | ||
82 | "id": "b3b3a79d-748a-4464-9471-732b6c74ec53", | 82 | "id": "b3b3a79d-748a-4464-9471-732b6c74ec53", | ||
83 | "image_url": | 83 | "image_url": | ||
84 | "2022-05-19-001030.456616FullColor1280x1024LogoOnly.png", | 84 | "2022-05-19-001030.456616FullColor1280x1024LogoOnly.png", | ||
85 | "is_organization": true, | 85 | "is_organization": true, | ||
86 | "name": "observatorio-metropolitano-centrogeo", | 86 | "name": "observatorio-metropolitano-centrogeo", | ||
87 | "state": "active", | 87 | "state": "active", | ||
88 | "title": "Observatorio Metropolitano CentroGeo", | 88 | "title": "Observatorio Metropolitano CentroGeo", | ||
89 | "type": "organization" | 89 | "type": "organization" | ||
90 | }, | 90 | }, | ||
91 | "owner_org": "b3b3a79d-748a-4464-9471-732b6c74ec53", | 91 | "owner_org": "b3b3a79d-748a-4464-9471-732b6c74ec53", | ||
92 | "private": false, | 92 | "private": false, | ||
93 | "relationships_as_object": [], | 93 | "relationships_as_object": [], | ||
94 | "relationships_as_subject": [], | 94 | "relationships_as_subject": [], | ||
t | 95 | "resources": [], | t | 95 | "resources": [ |
96 | { | ||||
97 | "cache_last_updated": null, | ||||
98 | "cache_url": null, | ||||
99 | "created": "2025-10-11T01:22:59.995592", | ||||
100 | "datastore_active": false, | ||||
101 | "description": "Artificial intelligence (AI) is currently being | ||||
102 | utilized in a wide range of sophisticated applications, but the | ||||
103 | outcomes of many AI models are challenging to comprehend and trust due | ||||
104 | to their black-box nature. Usually, it is essential to understand the | ||||
105 | reasoning behind an AI model's decision-making. Thus, the need for | ||||
106 | eXplainable AI (XAI) methods for improving trust in AI models has | ||||
107 | arisen. XAI has become a popular research subject within the AI field | ||||
108 | in recent years. Existing survey papers have tackled the concepts of | ||||
109 | XAI, its general terms, and post-hoc explainability methods but there | ||||
110 | have not been any reviews that have looked at the assessment methods, | ||||
111 | available tools, XAI datasets, and other related aspects. Therefore, | ||||
112 | in this comprehensive study, we provide readers with an overview of | ||||
113 | the current research and trends in this rapidly emerging area with a | ||||
114 | case study example. The study starts by explaining the background of | ||||
115 | XAI, common definitions, and summarizing recently proposed techniques | ||||
116 | in XAI for supervised machine learning. The review divides XAI | ||||
117 | techniques into four axes using a hierarchical categorization system: | ||||
118 | (i) data explainability, (ii) model explainability, (iii) post-hoc | ||||
119 | explainability, and (iv) assessment of explanations. We also introduce | ||||
120 | available evaluation metrics as well as open-source packages and | ||||
121 | datasets with future research directions. Then, the significance of | ||||
122 | explainability in terms of legal demands, user viewpoints, and | ||||
123 | application orientation is outlined, termed as XAI concerns. This | ||||
124 | paper advocates for tailoring explanation content to specific user | ||||
125 | types. An examination of XAI techniques and evaluation was conducted | ||||
126 | by looking at 410 critical articles, published between January 2016 | ||||
127 | and October 2022, in reputed journals and using a wide range of | ||||
128 | research databases as a source of information. The article is aimed at | ||||
129 | XAI researchers who are interested in making their AI models more | ||||
130 | trustworthy, as well as towards researchers from other disciplines who | ||||
131 | are looking for effective XAI methods to complete tasks with | ||||
132 | confidence while communicating meaning from data.", | ||||
133 | "format": "HTML", | ||||
134 | "hash": "", | ||||
135 | "id": "01060979-9e3f-43ec-a39c-84ba0fc3c013", | ||||
136 | "last_modified": null, | ||||
137 | "metadata_modified": "2025-10-11T01:22:59.984482", | ||||
138 | "mimetype": null, | ||||
139 | "mimetype_inner": null, | ||||
140 | "name": "Improved training of deep convolutional networks via | ||||
141 | minimum-variance regularized adaptive sampling", | ||||
142 | "package_id": "05827633-b5a8-4eca-b268-e47d7075f3ae", | ||||
143 | "position": 0, | ||||
144 | "resource_type": null, | ||||
145 | "size": null, | ||||
146 | "state": "active", | ||||
147 | "url": "https://doi.org/10.1088/2632-2153/ad092c/v1/review3", | ||||
148 | "url_type": null | ||||
149 | } | ||||
150 | ], | ||||
96 | "state": "active", | 151 | "state": "active", | ||
97 | "tags": [ | 152 | "tags": [ | ||
98 | { | 153 | { | ||
99 | "display_name": "artificial-intelligence", | 154 | "display_name": "artificial-intelligence", | ||
100 | "id": "47cb06d3-c2a4-42af-b633-03eea6181083", | 155 | "id": "47cb06d3-c2a4-42af-b633-03eea6181083", | ||
101 | "name": "artificial-intelligence", | 156 | "name": "artificial-intelligence", | ||
102 | "state": "active", | 157 | "state": "active", | ||
103 | "vocabulary_id": null | 158 | "vocabulary_id": null | ||
104 | }, | 159 | }, | ||
105 | { | 160 | { | ||
106 | "display_name": "computer-science", | 161 | "display_name": "computer-science", | ||
107 | "id": "29cae056-cd7e-43f7-be5b-b25869a3fbf2", | 162 | "id": "29cae056-cd7e-43f7-be5b-b25869a3fbf2", | ||
108 | "name": "computer-science", | 163 | "name": "computer-science", | ||
109 | "state": "active", | 164 | "state": "active", | ||
110 | "vocabulary_id": null | 165 | "vocabulary_id": null | ||
111 | }, | 166 | }, | ||
112 | { | 167 | { | ||
113 | "display_name": "trustworthiness", | 168 | "display_name": "trustworthiness", | ||
114 | "id": "b0eebfb2-112c-4eba-ab2f-f458f5555e98", | 169 | "id": "b0eebfb2-112c-4eba-ab2f-f458f5555e98", | ||
115 | "name": "trustworthiness", | 170 | "name": "trustworthiness", | ||
116 | "state": "active", | 171 | "state": "active", | ||
117 | "vocabulary_id": null | 172 | "vocabulary_id": null | ||
118 | } | 173 | } | ||
119 | ], | 174 | ], | ||
120 | "title": "Improved training of deep convolutional networks via | 175 | "title": "Improved training of deep convolutional networks via | ||
121 | minimum-variance regularized adaptive sampling", | 176 | minimum-variance regularized adaptive sampling", | ||
122 | "type": "dataset", | 177 | "type": "dataset", | ||
123 | "url": "https://doi.org/10.1088/2632-2153/ad092c/v1/review3", | 178 | "url": "https://doi.org/10.1088/2632-2153/ad092c/v1/review3", | ||
124 | "version": null | 179 | "version": null | ||
125 | } | 180 | } |