Figure - PMC

Skip to main content

An official website of the United States government

Here's how you know

Here's how you know

Official websites use .gov
A .gov website belongs to an official government organization in the United States.

Secure .gov websites use HTTPS
A lock ( ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

View full-text article in PMC

. 2014 Jun 17;8:43. doi: 10.3389/fnint.2014.00043

Search in PMC
Search in PubMed
View in NLM Catalog
Add to search

Copyright © 2014 Chang, Grossberg and Cao.

This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

PMC Copyright notice

Set of object stimuli for view- and positionally-invariant category learning. (A) Each object reflects the relative size within 100 × 100 pixels from Caltech 101 dataset. (B) A simulated scene for simulations of view-invariant object category learning in section 8.1. A scenic input image is partitioned into 25 regions (solid lines) and objects are located in the central regions of the input scene (regions 7, 8, 9, 12, 13, 14, 17, 18, and 19). Region 5 is the foveal region and others are the peripheral regions. (C) The bottom-up input representations after cellphone becomes the attended object and is foveated. (D) The bottom-up input representation when motorcycle becomes foveated after the soccer ball and cellphone are learned. (E,F) A sequence of simulated scenes for simulations of positionally- and view-invariant object category learning in section 8.2. Each scenic input only contains one object located in one of the center regions.