Hierarchical Modular Optimization of Convolutional Networks Achieves Representations Similar to Macaque IT and Human Ventral Stream
Humans recognize visually-presented objects rapidly and accurately. To understand this ability, we seek to construct models of the ventral stream, the series of cortical areas thought to subserve object recognition. One tool to assess the quality of a model of the ventral stream is the Representatio...
| Main Authors: | , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | en_US |
| Published: |
Neural Information Processing Systems Foundation
2015
|
| Online Access: | http://hdl.handle.net/1721.1/95910 https://orcid.org/0000-0002-1592-5896 https://orcid.org/0000-0001-7779-2219 |
| _version_ | 1826202569423192064 |
|---|---|
| author | Yamins, Daniel L. K. Hong, Ha Cadieu, Charles DiCarlo, James |
| author2 | Harvard University--MIT Division of Health Sciences and Technology |
| author_facet | Harvard University--MIT Division of Health Sciences and Technology Yamins, Daniel L. K. Hong, Ha Cadieu, Charles DiCarlo, James |
| author_sort | Yamins, Daniel L. K. |
| collection | MIT |
| description | Humans recognize visually-presented objects rapidly and accurately. To understand this ability, we seek to construct models of the ventral stream, the series of cortical areas thought to subserve object recognition. One tool to assess the quality of a model of the ventral stream is the Representational Dissimilarity Matrix (RDM), which uses a set of visual stimuli and measures the distances produced in either the brain (i.e. fMRI voxel responses, neural firing rates) or in models (fea-ures). Previous work has shown that all known models of the ventral stream fail to capture the RDM pattern observed in either IT cortex, the highest ventral area, or in the human ventral stream. In this work, we construct models of the ventral stream using a novel optimization procedure for category-level object recognition problems, and produce RDMs resembling both macaque IT and human ventral stream. The model, while novel in the optimization procedure, further develops a long-standing functional hypothesis that the ventral visual stream is a hierarchically arranged series of processing stages optimized for visual object recognition. |
| first_indexed | 2024-09-23T12:09:37Z |
| format | Article |
| id | mit-1721.1/95910 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T12:09:37Z |
| publishDate | 2015 |
| publisher | Neural Information Processing Systems Foundation |
| record_format | dspace |
| spelling | mit-1721.1/959102022-10-01T08:32:35Z Hierarchical Modular Optimization of Convolutional Networks Achieves Representations Similar to Macaque IT and Human Ventral Stream Yamins, Daniel L. K. Hong, Ha Cadieu, Charles DiCarlo, James Harvard University--MIT Division of Health Sciences and Technology Massachusetts Institute of Technology. Department of Brain and Cognitive Sciences McGovern Institute for Brain Research at MIT DiCarlo, James Yamins, Daniel L. K. Hong, Ha Cadieu, Charles DiCarlo, James Humans recognize visually-presented objects rapidly and accurately. To understand this ability, we seek to construct models of the ventral stream, the series of cortical areas thought to subserve object recognition. One tool to assess the quality of a model of the ventral stream is the Representational Dissimilarity Matrix (RDM), which uses a set of visual stimuli and measures the distances produced in either the brain (i.e. fMRI voxel responses, neural firing rates) or in models (fea-ures). Previous work has shown that all known models of the ventral stream fail to capture the RDM pattern observed in either IT cortex, the highest ventral area, or in the human ventral stream. In this work, we construct models of the ventral stream using a novel optimization procedure for category-level object recognition problems, and produce RDMs resembling both macaque IT and human ventral stream. The model, while novel in the optimization procedure, further develops a long-standing functional hypothesis that the ventral visual stream is a hierarchically arranged series of processing stages optimized for visual object recognition. 2015-03-06T19:34:13Z 2015-03-06T19:34:13Z 2013 Article http://purl.org/eprint/type/ConferencePaper http://hdl.handle.net/1721.1/95910 Yamins, Daniel, Ha Hong, Charles Cadieu, and James J. Dicarlo. "Hierarchical Modular Optimization of Convolutional Networks Achieves Representations Similar to Macaque IT and Human Ventral Stream." Advances in Neural Information Processing Systems (NIPS) 26 (2013). https://orcid.org/0000-0002-1592-5896 https://orcid.org/0000-0001-7779-2219 en_US http://papers.nips.cc/paper/4991-hierarchical-modular-optimization-of-convolutional-networks-achieves-representations-similar-to-macaque-it-and-human-ventral-stream Advances in Neural Information Processing Systems (NIPS) 26 Creative Commons Attribution-Noncommercial-Share Alike http://creativecommons.org/licenses/by-nc-sa/4.0/ application/pdf Neural Information Processing Systems Foundation DiCarlo via Courtney Crummett |
| spellingShingle | Yamins, Daniel L. K. Hong, Ha Cadieu, Charles DiCarlo, James Hierarchical Modular Optimization of Convolutional Networks Achieves Representations Similar to Macaque IT and Human Ventral Stream |
| title | Hierarchical Modular Optimization of Convolutional Networks Achieves Representations Similar to Macaque IT and Human Ventral Stream |
| title_full | Hierarchical Modular Optimization of Convolutional Networks Achieves Representations Similar to Macaque IT and Human Ventral Stream |
| title_fullStr | Hierarchical Modular Optimization of Convolutional Networks Achieves Representations Similar to Macaque IT and Human Ventral Stream |
| title_full_unstemmed | Hierarchical Modular Optimization of Convolutional Networks Achieves Representations Similar to Macaque IT and Human Ventral Stream |
| title_short | Hierarchical Modular Optimization of Convolutional Networks Achieves Representations Similar to Macaque IT and Human Ventral Stream |
| title_sort | hierarchical modular optimization of convolutional networks achieves representations similar to macaque it and human ventral stream |
| url | http://hdl.handle.net/1721.1/95910 https://orcid.org/0000-0002-1592-5896 https://orcid.org/0000-0001-7779-2219 |
| work_keys_str_mv | AT yaminsdaniellk hierarchicalmodularoptimizationofconvolutionalnetworksachievesrepresentationssimilartomacaqueitandhumanventralstream AT hongha hierarchicalmodularoptimizationofconvolutionalnetworksachievesrepresentationssimilartomacaqueitandhumanventralstream AT cadieucharles hierarchicalmodularoptimizationofconvolutionalnetworksachievesrepresentationssimilartomacaqueitandhumanventralstream AT dicarlojames hierarchicalmodularoptimizationofconvolutionalnetworksachievesrepresentationssimilartomacaqueitandhumanventralstream |