Real-world visual input consists of rich scenes that are meaningfully composed of multiple
objects that interact in complex but predictable ways. Despite this complexity, humans can …

The free energy principle and its corollary, the active inference framework, serve as
theoretical foundations in the domain of neuroscience, explaining the genesis of intelligent …

Abstract Information gathering comprises actions whose (sensory) consequences resolve
uncertainty (ie, are salient). In other words, actions that solicit salient information cause the …

The properties of the human eye retina, including space-variant resolution and gaze
characters, provide many advantages for numerous applications that simultaneously require …

While abundant in biology, foveated vision is nearly absent from computational models and
especially deep learning architectures. Despite considerable hardware improvements …

Foveation can be defined as the organic action of directing the gaze towards a visual region
of interest to acquire relevant information selectively. With the recent advent of event …

Visual search is an essential cognitive ability, offering a prototypical control problem to be
addressed with Active Inference. Under a Naive Bayes assumption, the maximization of the …

Humans are able to categorize images very efficiently, in particular to detect the presence of
an animal very quickly. Recently, deep learning algorithms based on convolutional neural …

Decoding the semantic content of images is nowadays dominated by the use of deep
convolutional neural networks (DCNNs), However, their generalization capability is still …

This paper presents the design and implementation of a 128× 128 electronically foveated
dynamic vision sensor (EF-DVS) fabricated using 350 nm CMOS technology. The EF-DVS …