{"id":400862,"date":"2024-10-20T04:53:00","date_gmt":"2024-10-20T04:53:00","guid":{"rendered":"https:\/\/pdfstandards.shop\/product\/uncategorized\/ieee-2941-2021\/"},"modified":"2024-10-26T08:40:26","modified_gmt":"2024-10-26T08:40:26","slug":"ieee-2941-2021","status":"publish","type":"product","link":"https:\/\/pdfstandards.shop\/product\/publishers\/ieee\/ieee-2941-2021\/","title":{"rendered":"IEEE 2941-2021"},"content":{"rendered":"

New IEEE Standard – Active. The AI development interface, AI model interoperable representation, coding format, and model encapsulated format for efficient AI model inference, storage, distribution, and management are discussed in this standard.<\/p>\n

PDF Catalog<\/h4>\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n
PDF Pages<\/th>\nPDF Title<\/th>\n<\/tr>\n
1<\/td>\nIEEE Std 2941-2021 Front Cover <\/td>\n<\/tr>\n
2<\/td>\nTitle page <\/td>\n<\/tr>\n
4<\/td>\nImportant Notices and Disclaimers Concerning IEEE Standards Documents
Notice and Disclaimer of Liability Concerning the Use of IEEE Standards Documents <\/td>\n<\/tr>\n
5<\/td>\nTranslations
Official statements
Comments on standards
Laws and regulations
Data privacy
Copyrights <\/td>\n<\/tr>\n
6<\/td>\nPhotocopies
Updating of IEEE Standards documents
Errata
Patents
IMPORTANT NOTICE <\/td>\n<\/tr>\n
7<\/td>\nParticipants
Participants <\/td>\n<\/tr>\n
8<\/td>\nIntroduction <\/td>\n<\/tr>\n
9<\/td>\nContents <\/td>\n<\/tr>\n
11<\/td>\n1. Overview
1.1 Scope
1.2 Purpose
1.3 Word usage <\/td>\n<\/tr>\n
12<\/td>\n2. Normative references
3. Definitions, acronyms, and abbreviations
3.1 Definitions <\/td>\n<\/tr>\n
14<\/td>\n3.2 Acronyms and abbreviations
4. Symbols and operators
4.1 Arithmetic operators <\/td>\n<\/tr>\n
15<\/td>\n4.2 Logical operator
4.3 Relational operators <\/td>\n<\/tr>\n
16<\/td>\n4.4 Bitwise operators
4.5 Assignment operators
5. Framework of convolutional neural network representation and model compression <\/td>\n<\/tr>\n
17<\/td>\n6. Syntax and semantics of neural network models
6.1 Data structure
6.1.1 Data structure of neural network structure <\/td>\n<\/tr>\n
18<\/td>\n6.1.2 Data structure of neural network parameters <\/td>\n<\/tr>\n
19<\/td>\n6.2 Syntax description
6.2.1 Overview <\/td>\n<\/tr>\n
20<\/td>\n6.2.2 Definition of model structure
6.2.3 Definition of contributor list
6.2.4 Definition of computational graph <\/td>\n<\/tr>\n
21<\/td>\n6.2.5 Definition of operator node
6.2.6 Definition of variable node
6.2.7 Definition of attribute <\/td>\n<\/tr>\n
22<\/td>\n6.2.8 Definition of other type
6.2.9 Definition of tensor type <\/td>\n<\/tr>\n
23<\/td>\n6.2.10 Definition of tensor
6.2.11 Definition of tensor size <\/td>\n<\/tr>\n
24<\/td>\n6.2.12 Definition of dimension
6.3 Semantic description <\/td>\n<\/tr>\n
71<\/td>\n6.4 Definition of training operator
6.4.1 Loss function <\/td>\n<\/tr>\n
73<\/td>\n6.4.2 Definition of inverse operator <\/td>\n<\/tr>\n
75<\/td>\n7. Compression process
7.1 Multiple models
7.1.1 Definition of multiple models technology <\/td>\n<\/tr>\n
76<\/td>\n7.1.2 Compression of multiple models <\/td>\n<\/tr>\n
77<\/td>\n7.1.3 Shared compression operator for weights of multiple model layers
7.1.3.1 Definition
7.1.3.2 Weight aggregation <\/td>\n<\/tr>\n
79<\/td>\n7.1.4 Residual quantization compression
7.1.4.1 Definition of residual quantization for multiple models
7.1.4.2 Weight sharing <\/td>\n<\/tr>\n
81<\/td>\n7.2 Quantization
7.2.1 Definition <\/td>\n<\/tr>\n
82<\/td>\n7.2.2 Basic quantization operator <\/td>\n<\/tr>\n
83<\/td>\n7.2.2.1 Linear quantization <\/td>\n<\/tr>\n
84<\/td>\n7.2.2.2 Codebook quantization <\/td>\n<\/tr>\n
86<\/td>\n7.2.3 Parameter quantization operator
7.2.3.1 Nonlinear function mapping <\/td>\n<\/tr>\n
88<\/td>\n7.2.3.2 INT4 parameter quantization <\/td>\n<\/tr>\n
90<\/td>\n7.2.3.3 Parameter quantization for bounded ReLU <\/td>\n<\/tr>\n
91<\/td>\n7.2.4 Activate quantization operator
7.2.4.1 Trainable alpha quantization
7.2.4.2 INT4 activation quantization <\/td>\n<\/tr>\n
93<\/td>\n7.2.4.3 Activation quantization for bounded ReLU <\/td>\n<\/tr>\n
95<\/td>\n7.2.4.4 Ratio synchronization quantization <\/td>\n<\/tr>\n
97<\/td>\n7.3 Pruning
7.3.1 Overview <\/td>\n<\/tr>\n
98<\/td>\n7.3.2 Pruning operator <\/td>\n<\/tr>\n
100<\/td>\n7.4 Structured matrix
7.4.1 Structured matrix compression <\/td>\n<\/tr>\n
101<\/td>\n7.4.2 Method for the compression of block circulant matrix with signed vectors
7.4.2.1 Block circulant matrix compression operator <\/td>\n<\/tr>\n
102<\/td>\n7.4.2.2 Random vector dimension list and random vector generation operator <\/td>\n<\/tr>\n
104<\/td>\n7.4.3 Method for the low-rank sparse decomposed structured matrix
7.4.3.1 Definition
7.4.3.2 Decomposition compression operator for the convolutional layers in low-rank sparse decomposed structured matrix <\/td>\n<\/tr>\n
106<\/td>\n7.4.3.3 Compression operator of a fully connected or 1 \u00d7 1 convolutional layer in a low-rank sparse decomposed structured matrix <\/td>\n<\/tr>\n
107<\/td>\n8. Decompression process
8.1 Multiple models
8.1.1 Decompression for multiple models <\/td>\n<\/tr>\n
108<\/td>\n8.1.2 Decompression operator for weights of multiple model layers
8.1.2.1 Decompression for weights of multiple model layers
8.1.2.2 Decompression output multiple models <\/td>\n<\/tr>\n
110<\/td>\n8.1.2.3 Decompression output specific model <\/td>\n<\/tr>\n
111<\/td>\n8.1.2.4 Decompression output switched specific models <\/td>\n<\/tr>\n
112<\/td>\n8.1.3 Decompression of residual quantization for multiple models
8.1.3.1 Definition of decompression
8.1.3.2 Decompression of the output target model <\/td>\n<\/tr>\n
113<\/td>\n8.2 Dequantization
8.2.1 Definition
8.2.2 Basic dequantization operator <\/td>\n<\/tr>\n
115<\/td>\n8.2.2.1 Linear dequantization <\/td>\n<\/tr>\n
116<\/td>\n8.2.2.2 Codebook dequantization <\/td>\n<\/tr>\n
117<\/td>\n8.2.3 Parameter dequantization operator
8.2.3.1 Nonlinear function mapping dequantization <\/td>\n<\/tr>\n
118<\/td>\n8.2.3.2 INT4 parameter dequantization <\/td>\n<\/tr>\n
119<\/td>\n8.2.4 Activate dequantization operator
8.2.4.1 Trainable alpha value dequantization <\/td>\n<\/tr>\n
120<\/td>\n8.2.4.2 INT4 activation dequantization <\/td>\n<\/tr>\n
121<\/td>\n8.3 Inverse sparsity\/inverse pruning operator
8.3.1 Definition <\/td>\n<\/tr>\n
122<\/td>\n8.3.2 Inverse sparsity <\/td>\n<\/tr>\n
123<\/td>\n8.4 Structured matrix
8.4.1 Decompression of structured matrix <\/td>\n<\/tr>\n
124<\/td>\n8.4.2 Method for the decompression of block circulant matrix with signed vectors
8.4.2.1 Block circulant matrix decompression operator <\/td>\n<\/tr>\n
126<\/td>\n8.4.2.2 Disturbance vector generation operator <\/td>\n<\/tr>\n
128<\/td>\n8.4.2.3 Operator on the layers using signed vector and block circulant matrix techniques <\/td>\n<\/tr>\n
129<\/td>\n8.4.3 Methods for the decompression of low-rank sparse decomposed structured matrix
8.4.3.1 Overview
8.4.3.2 Decompression operator for low-rank sparse decomposed structured matrix <\/td>\n<\/tr>\n
130<\/td>\n8.4.3.3 Decompression operator for the fully connected and 1 \u00d7 1 layers in low-rank sparse decomposed structured matrix <\/td>\n<\/tr>\n
131<\/td>\n9. Data generation
9.1 Definition
9.2 Training data generation method
9.2.1 Method of generating training data based on real data
9.2.1.1 Overview
9.2.1.2 Data augmentation method <\/td>\n<\/tr>\n
133<\/td>\n9.2.1.3 Generating data using the GAN <\/td>\n<\/tr>\n
135<\/td>\n9.2.2 Data-free training data generation method
9.2.2.1 Overview
9.2.2.2 Generating training data using the GAN <\/td>\n<\/tr>\n
138<\/td>\n9.3 Multiple models
9.3.1 Method for weight generation in multiple models
9.3.1.1 Multiple models weight update operator <\/td>\n<\/tr>\n
139<\/td>\n9.3.1.2 Multiple models weight shared data generation approach 1 <\/td>\n<\/tr>\n
141<\/td>\n9.3.1.3 Multiple models weight shared data generation approach 2 <\/td>\n<\/tr>\n
143<\/td>\n9.3.2 Residual quantization training method for multiple models <\/td>\n<\/tr>\n
144<\/td>\n9.4 Quantization
9.4.1 Parameter quantization
9.4.1.1 Data generation for INT4 parameter quantization <\/td>\n<\/tr>\n
150<\/td>\n9.4.1.2 Interval shrinkage quantization data generation <\/td>\n<\/tr>\n
154<\/td>\n9.4.2 Activate quantization
9.4.2.1 Data generation for INT4 activate quantization <\/td>\n<\/tr>\n
158<\/td>\n9.4.2.2 Trainable alpha quantization training data generation <\/td>\n<\/tr>\n
159<\/td>\n9.5 Pruning
9.5.1 Overview <\/td>\n<\/tr>\n
160<\/td>\n9.5.2 Sparse data generation method <\/td>\n<\/tr>\n
163<\/td>\n9.5.3 Incremental regularization pruning <\/td>\n<\/tr>\n
167<\/td>\n9.6 Structured matrix
9.6.1 Data generation of structured matrix <\/td>\n<\/tr>\n
168<\/td>\n9.6.2 Approach for generating data to be compressed in block circulant matrix with signed vectors <\/td>\n<\/tr>\n
172<\/td>\n9.6.3 Approach for generating the weight in low-rank sparse decomposed structured matrix
9.6.3.1 Overview <\/td>\n<\/tr>\n
173<\/td>\n9.6.3.2 Approaches for determining hyper-parameter R1, R2, groups and core_size
9.6.3.3 Process for the generation of weights of a low-rank sparse decomposed structured matrix <\/td>\n<\/tr>\n
175<\/td>\n10. Compressed representation of neural network
10.1 Specification of syntax and semantics <\/td>\n<\/tr>\n
180<\/td>\n10.2 Synatx
10.2.1 Neural network compression (NNC) bitstream syntax <\/td>\n<\/tr>\n
181<\/td>\n10.2.2 NNC header syntax <\/td>\n<\/tr>\n
182<\/td>\n10.2.3 NNC layer header syntax <\/td>\n<\/tr>\n
183<\/td>\n10.2.4 NNC 1D array syntax
10.2.5 NNC CTU3D syntax
10.2.6 NNC CTU3D header syntax <\/td>\n<\/tr>\n
184<\/td>\n10.2.7 NNC zdep_array syntax <\/td>\n<\/tr>\n
185<\/td>\n10.2.8 NNC CU3D syntax <\/td>\n<\/tr>\n
186<\/td>\n10.2.9 NNC predicted_codebook syntax
10.2.10 NNC sygnalled_codebook syntax <\/td>\n<\/tr>\n
187<\/td>\n10.2.11 NNC unitree3d syntax <\/td>\n<\/tr>\n
188<\/td>\n10.2.12 NNC octree3d syntax <\/td>\n<\/tr>\n
190<\/td>\n10.2.13 NNC tagtree3d syntax <\/td>\n<\/tr>\n
192<\/td>\n10.2.14 NNC uni_tagtree3d syntax <\/td>\n<\/tr>\n
194<\/td>\n10.2.15 NNC escape syntax
10.3 Semantics
10.3.1 Initialization
10.3.2 NNC bitstream semantics <\/td>\n<\/tr>\n
195<\/td>\n10.3.3 NNC header semantics
10.3.4 NNC layer header semantics <\/td>\n<\/tr>\n
196<\/td>\n10.3.5 NNC 1D array semantics
10.3.6 NNC CTU3D semantics
10.3.7 NNC CU3D header semantics
10.3.8 NNC zdep_array semantics
10.3.9 NNC CU3D semantics <\/td>\n<\/tr>\n
197<\/td>\n10.3.10 NNC predicted codebook semantics
10.3.11 NNC signaled codebook semantics
10.3.12 NNC unitree3d semantics <\/td>\n<\/tr>\n
199<\/td>\n10.3.13 NNC octree3d semantics <\/td>\n<\/tr>\n
200<\/td>\n10.3.14 NNC tagtree3d semantics <\/td>\n<\/tr>\n
202<\/td>\n10.3.15 NNC uni_tagtree3d semantics <\/td>\n<\/tr>\n
203<\/td>\n10.3.16 NNC escape semantics <\/td>\n<\/tr>\n
204<\/td>\n10.4 Parsing process
10.4.1 Description
10.4.2 Initialization
10.4.2.1 Initialization of context model
10.4.2.2 Initialization of AEC decoder
10.4.3 Parsing binary string
10.4.3.1 Description <\/td>\n<\/tr>\n
205<\/td>\n10.4.3.2 Determine ctxIdx <\/td>\n<\/tr>\n
208<\/td>\n10.4.3.3 Parsing bins
10.4.3.3.1 Parsing process
10.4.3.3.2 decode_decision <\/td>\n<\/tr>\n
209<\/td>\n10.4.3.3.3 decode_aec_stuffing_bit
10.4.3.3.4 decode_bypass
10.4.3.3.5 update_ctx <\/td>\n<\/tr>\n
210<\/td>\n10.4.3.4 Binarization
10.4.3.4.1 Description <\/td>\n<\/tr>\n
212<\/td>\n10.4.3.4.2 Binarization for fix length code (FL)
10.4.3.4.3 Binarization for unary code (U) <\/td>\n<\/tr>\n
213<\/td>\n10.4.3.4.4 Binarization for truncated unary code (TU)
10.4.3.4.5 kth-order Exp-Golomb codes (EGk) <\/td>\n<\/tr>\n
214<\/td>\n10.4.3.4.6 Joint truncated unary code and kth-order Exp-Golomb codes (UEGk) <\/td>\n<\/tr>\n
215<\/td>\n10.5 Decoding process
10.5.1 General decoding process
10.5.2 Decoding NNC header
10.5.3 Decoding NNC layer header
10.5.4 Decoding NNC sublayer <\/td>\n<\/tr>\n
217<\/td>\n10.5.5 Decoding 1D array
10.5.6 NNC CTU3D semantics <\/td>\n<\/tr>\n
218<\/td>\n10.5.7 Decoding CTU3D
10.5.8 Decoding ZdepArray
10.5.9 Decoding CU3D <\/td>\n<\/tr>\n
219<\/td>\n10.5.10 Decoding predicted codebook
10.5.11 Decoding signalled codebook
10.5.12 Decoding unitree3d <\/td>\n<\/tr>\n
220<\/td>\n10.5.13 Decoding octree3d
10.5.14 Decoding tagtree3d
10.5.15 Decoding uni_tagtree3d <\/td>\n<\/tr>\n
221<\/td>\n10.5.16 Decoding escape <\/td>\n<\/tr>\n
222<\/td>\n11. Model protection
11.1 Model protection definition <\/td>\n<\/tr>\n
223<\/td>\n11.2 Model encryption process <\/td>\n<\/tr>\n
224<\/td>\n11.3 Model decryption process <\/td>\n<\/tr>\n
225<\/td>\n11.4 Cipher model data structure definition <\/td>\n<\/tr>\n
226<\/td>\nBack Cover <\/td>\n<\/tr>\n<\/table>\n","protected":false},"excerpt":{"rendered":"

IEEE Standard for Artificial Intelligence (AI) Model Representation, Compression, Distribution, and Management<\/b><\/p>\n\n\n\n\n
Published By<\/td>\nPublication Date<\/td>\nNumber of Pages<\/td>\n<\/tr>\n
IEEE<\/b><\/a><\/td>\n2021<\/td>\n226<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n","protected":false},"featured_media":400867,"template":"","meta":{"rank_math_lock_modified_date":false,"ep_exclude_from_search":false},"product_cat":[2644],"product_tag":[],"class_list":{"0":"post-400862","1":"product","2":"type-product","3":"status-publish","4":"has-post-thumbnail","6":"product_cat-ieee","8":"first","9":"instock","10":"sold-individually","11":"shipping-taxable","12":"purchasable","13":"product-type-simple"},"_links":{"self":[{"href":"https:\/\/pdfstandards.shop\/wp-json\/wp\/v2\/product\/400862","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/pdfstandards.shop\/wp-json\/wp\/v2\/product"}],"about":[{"href":"https:\/\/pdfstandards.shop\/wp-json\/wp\/v2\/types\/product"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/pdfstandards.shop\/wp-json\/wp\/v2\/media\/400867"}],"wp:attachment":[{"href":"https:\/\/pdfstandards.shop\/wp-json\/wp\/v2\/media?parent=400862"}],"wp:term":[{"taxonomy":"product_cat","embeddable":true,"href":"https:\/\/pdfstandards.shop\/wp-json\/wp\/v2\/product_cat?post=400862"},{"taxonomy":"product_tag","embeddable":true,"href":"https:\/\/pdfstandards.shop\/wp-json\/wp\/v2\/product_tag?post=400862"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}