Class information for: |
Basic class information |
| Class id | #P | Avg. number of references |
Database coverage of references |
|---|---|---|---|
| 23468 | 345 | 21.8 | 39% |
Hierarchy of classes |
The table includes all classes above and classes immediately below the current class. |
Terms with highest relevance score |
| rank | Term | termType | Chi square | Shr. of publ. in class containing term |
Class's shr. of term's tot. occurrences |
#P with term in class |
|---|---|---|---|---|---|---|
| 1 | NEOCOGNITRON | authKW | 1869714 | 8% | 81% | 26 |
| 2 | DYNAMIC LINK MATCHING | authKW | 283223 | 1% | 80% | 4 |
| 3 | VISUAL PATTERN RECOGNITION | authKW | 275724 | 3% | 35% | 9 |
| 4 | MNIST DATABASE | authKW | 265523 | 1% | 100% | 3 |
| 5 | ECOLOGICAL THEORY OF PERCEPTION | authKW | 177015 | 1% | 100% | 2 |
| 6 | INTERPOLATING VECTOR | authKW | 177015 | 1% | 100% | 2 |
| 7 | MICRODEVICE ASSEMBLY | authKW | 177015 | 1% | 100% | 2 |
| 8 | MICROMECH MECHATRON | address | 177015 | 1% | 100% | 2 |
| 9 | NON UNIFORM BLUR | authKW | 177015 | 1% | 100% | 2 |
| 10 | POSITION NORMALIZATION | authKW | 177015 | 1% | 100% | 2 |
Web of Science journal categories |
| Rank | Term | Chi square | Shr. of publ. in class containing term |
Class's shr. of term's tot. occurrences |
#P with term in class |
|---|---|---|---|---|---|
| 1 | Computer Science, Artificial Intelligence | 13895 | 52% | 0% | 180 |
| 2 | Computer Science, Cybernetics | 1569 | 6% | 0% | 22 |
| 3 | Engineering, Electrical & Electronic | 639 | 27% | 0% | 92 |
| 4 | Computer Science, Theory & Methods | 393 | 10% | 0% | 34 |
| 5 | Neurosciences | 270 | 18% | 0% | 63 |
| 6 | Computer Science, Information Systems | 211 | 7% | 0% | 24 |
| 7 | Computer Science, Interdisciplinary Applications | 114 | 6% | 0% | 19 |
| 8 | Computer Science, Software Engineering | 83 | 4% | 0% | 14 |
| 9 | Computer Science, Hardware & Architecture | 74 | 3% | 0% | 10 |
| 10 | Engineering, General | 42 | 3% | 0% | 11 |
Address terms |
| Rank | Term | Chi square | Shr. of publ. in class containing term |
Class's shr. of term's tot. occurrences |
#P with term in class |
|---|---|---|---|---|---|
| 1 | MICROMECH MECHATRON | 177015 | 1% | 100% | 2 |
| 2 | PL SCI TECHNOL DEV | 105359 | 1% | 24% | 5 |
| 3 | BIOMED SIGNAL PROCBIOELECT | 88508 | 0% | 100% | 1 |
| 4 | BRAIN SCI STR | 88508 | 0% | 100% | 1 |
| 5 | COMP TECHNOL INFORMAT | 88508 | 0% | 100% | 1 |
| 6 | EEPIS | 88508 | 0% | 100% | 1 |
| 7 | IMAGE PROD RADIOL | 88508 | 0% | 100% | 1 |
| 8 | MUS MEDIAARTS | 88508 | 0% | 100% | 1 |
| 9 | INT TRAINING INFORMAT TECHNOL SYST | 81943 | 1% | 19% | 5 |
| 10 | COMP VIS ARTIFICIAL INTELLIGENCE | 59002 | 1% | 33% | 2 |
Journals |
| Rank | Term | Chi square | Shr. of publ. in class containing term |
Class's shr. of term's tot. occurrences |
#P with term in class |
|---|---|---|---|---|---|
| 1 | NEURAL NETWORKS | 38491 | 11% | 1% | 37 |
| 2 | IEEE TRANSACTIONS ON NEURAL NETWORKS | 12245 | 6% | 1% | 20 |
| 3 | NEUROCOMPUTING | 6226 | 8% | 0% | 26 |
| 4 | BIOLOGICAL CYBERNETICS | 4935 | 4% | 0% | 13 |
| 5 | PATTERN RECOGNITION LETTERS | 4415 | 5% | 0% | 17 |
| 6 | JOURNAL OF THE INSTITUTION OF ELECTRONICS AND TELECOMMUNICATION ENGINEERS | 3048 | 1% | 2% | 2 |
| 7 | NEURAL NETWORK WORLD | 3012 | 1% | 1% | 4 |
| 8 | SYSTEMS AND COMPUTERS IN JAPAN | 2515 | 1% | 1% | 3 |
| 9 | INTERNATIONAL JOURNAL OF NEURAL SYSTEMS | 2265 | 1% | 1% | 4 |
| 10 | PATTERN RECOGNITION | 2168 | 4% | 0% | 13 |
Author Key Words |
| Rank | Term | Chi square | Shr. of publ. in class containing term |
Class's shr. of term's tot. occurrences |
#P with term in class |
LCSH search | Wikipedia search |
|---|---|---|---|---|---|---|---|
| 1 | NEOCOGNITRON | 1869714 | 8% | 81% | 26 | Search NEOCOGNITRON | Search NEOCOGNITRON |
| 2 | DYNAMIC LINK MATCHING | 283223 | 1% | 80% | 4 | Search DYNAMIC+LINK+MATCHING | Search DYNAMIC+LINK+MATCHING |
| 3 | VISUAL PATTERN RECOGNITION | 275724 | 3% | 35% | 9 | Search VISUAL+PATTERN+RECOGNITION | Search VISUAL+PATTERN+RECOGNITION |
| 4 | MNIST DATABASE | 265523 | 1% | 100% | 3 | Search MNIST+DATABASE | Search MNIST+DATABASE |
| 5 | ECOLOGICAL THEORY OF PERCEPTION | 177015 | 1% | 100% | 2 | Search ECOLOGICAL+THEORY+OF+PERCEPTION | Search ECOLOGICAL+THEORY+OF+PERCEPTION |
| 6 | INTERPOLATING VECTOR | 177015 | 1% | 100% | 2 | Search INTERPOLATING+VECTOR | Search INTERPOLATING+VECTOR |
| 7 | MICRODEVICE ASSEMBLY | 177015 | 1% | 100% | 2 | Search MICRODEVICE+ASSEMBLY | Search MICRODEVICE+ASSEMBLY |
| 8 | NON UNIFORM BLUR | 177015 | 1% | 100% | 2 | Search NON+UNIFORM+BLUR | Search NON+UNIFORM+BLUR |
| 9 | POSITION NORMALIZATION | 177015 | 1% | 100% | 2 | Search POSITION+NORMALIZATION | Search POSITION+NORMALIZATION |
| 10 | WINNER KILL LOSER | 177015 | 1% | 100% | 2 | Search WINNER+KILL+LOSER | Search WINNER+KILL+LOSER |
Core articles |
The table includes core articles in the class. The following variables is taken into account for the relevance score of an article in a cluster c: (1) Number of references referring to publications in the class. (2) Share of total number of active references referring to publications in the class. (3) Age of the article. New articles get higher score than old articles. (4) Citation rate, normalized to year. |
| Rank | Reference | # ref. in cl. |
Shr. of ref. in cl. |
Citations |
|---|---|---|---|---|
| 1 | GOLTSEV, A , GRITSENKO, V , (2012) INVESTIGATION OF EFFICIENT FEATURES FOR IMAGE RECOGNITION BY NEURAL NETWORKS.NEURAL NETWORKS. VOL. 28. ISSUE . P. 15-23 | 10 | 77% | 5 |
| 2 | FUKUSHIMA, K , (2013) ARTIFICIAL VISION BY MULTI-LAYERED NEURAL NETWORKS: NEOCOGNITRON AND ITS ADVANCES.NEURAL NETWORKS. VOL. 37. ISSUE . P. 103-119 | 13 | 50% | 16 |
| 3 | FUKUSHIMA, K , (2003) NEOCOGNITRON FOR HANDWRITTEN DIGIT RECOGNITION.NEUROCOMPUTING. VOL. 51. ISSUE . P. 161 -180 | 10 | 63% | 55 |
| 4 | CARDOSO, A , WICHERT, A , (2010) NEOCOGNITRON AND THE MAP TRANSFORMATION CASCADE.NEURAL NETWORKS. VOL. 23. ISSUE 1. P. 74 -88 | 7 | 78% | 1 |
| 5 | GOLTSEV, A , GRITSENKO, V , (2015) MODULAR NEURAL NETWORKS WITH RADIAL NEURAL COLUMNAR ARCHITECTURE.BIOLOGICALLY INSPIRED COGNITIVE ARCHITECTURES. VOL. 13. ISSUE . P. 63 -74 | 10 | 48% | 0 |
| 6 | FUKUSHIMA, K , (2013) TRAINING MULTI-LAYERED NEURAL NETWORK NEOCOGNITRON.NEURAL NETWORKS. VOL. 40. ISSUE . P. 18-31 | 7 | 58% | 11 |
| 7 | FUKUSHIMA, K , (2011) INCREASING ROBUSTNESS AGAINST BACKGROUND NOISE: VISUAL PATTERN RECOGNITION BY A NEOCOGNITRON.NEURAL NETWORKS. VOL. 24. ISSUE 7. P. 767-778 | 8 | 53% | 5 |
| 8 | FUKUSHIMA, K , HAYASHI, I , LEVEILLE, J , (2014) NEOCOGNITRON TRAINED BY WINNER-KILL-LOSER WITH TRIPLE THRESHOLD.NEUROCOMPUTING. VOL. 129. ISSUE . P. 78-84 | 4 | 100% | 0 |
| 9 | BOLOURI, H , SABISCH, T , FERGUSON, A , (2000) IDENTIFICATION OF COMPLEX SHAPES USING A SELF ORGANIZING NEURAL SYSTEM.IEEE TRANSACTIONS ON NEURAL NETWORKS. VOL. 11. ISSUE 4. P. 921 -934 | 9 | 64% | 4 |
| 10 | WOOD, J , (1999) THE GROUP REPRESENTATION NETWORK: A GENERAL APPROACH TO INVARIANT PATTERN CLASSIFICATION.ADVANCES IN IMAGING AND ELECTRON PHYSICS, VOL 107. VOL. 107. ISSUE . P. 309 -+ | 10 | 59% | 0 |
Classes with closest relation at Level 1 |