Sentence examples for models of invariant from inspiring English sources

Then we illustrate how models of invariant visual object recognition can be tested to reveal whether they account for these properties.

At the beginning of this paper, we listed some of the key properties of inferior temporal cortex (IT) neurons that need to be addressed by models of invariant visual object recognition in the ventral visual stream of the cerebral cortex.

These findings and the conceptual points that we make have clear implications for what needs to be solved by future models of invariant visual object recognition in the ventral cortical visual stream.

This key property is essential for recognizing a particular person or object and is frequently not addressed in models of invariant object recognition, which still focus on classification into, e.g. animal versus non-animal, hats versus bears versus beer mugs (Serre et al. 2007c, a, b ; Mutch and Lowe 2008 ; Yamins et al. 2014 ).

This key property is essential for recognizing a particular person or object and is frequently not addressed in models of invariant object recognition, which still focus on classification into, e.g. animal versus non-animal, or classes such as hats and bears from databases such as the CalTech (Serre et al. 2007a, b; Mutch and Lowe 2008; Serre et al. 2007c; Yamins et al. 2014).

We next summarize some of the key and fundamental properties of the responses of primate inferior temporal cortex (IT) neurons (Rolls 2008, 2012a; Rolls and Treves 2011) that need to be addressed by biologically plausible models of invariant visual object recognition.

We establish a short exact sequence to relate the germ model of invariant subspaces of a Hilbert space of vector-valued analytic functions and the sheaf model of the corresponding coinvariant subspaces.

Recently, the notion of an array-based system has been introduced as an abstraction of infinite state systems (such as mutual exclusion protocols or sorting programs) which allows for model checking of invariant (safety) and recurrence (liveness) properties by Satisfiability Modulo Theories (SMT) techniques.

The same phylogeny was obtained from a 16s RNA alignment using maximum likelihood as implemented in Phyml [ 31] using the HKY model, estimation of invariant sites, and among site rate variation described by a gamma distribution with estimated shape parameter.

GTR, general time-reversible model; HKY, the Hasegawa, Kishino, and Yano model; I, proportion of invariant sites; G, gamma distribution.

Specifically, we focus on the question of how the autonomous learning of invariant models can be embedded into a performing system and how such models can be used to define object-specific attentional modulation signals.