The document summarizes research on hierarchical models for object recognition, including:
- Hierarchies are inspired by the primate visual system which uses hierarchies of features of increasing complexity.
- Convolutional neural networks and the Neocognitron model use hierarchical architectures with layers of feature extraction.
- Learning hierarchical compositional representations allows constructing objects from reusable parts.
- Identifying images from brain activity showed it is possible to predict fMRI activity and identify images based on a voxel activity model.