Abstract We introduce the Generalized Discrimination Value (GDV) that measures, in a non-
invasive manner, how well different data classes separate in each given layer of an artificial …

In the last few years, spiking neural networks (SNNs) have been demonstrated to perform on
par with regular convolutional neural networks. Several works have proposed methods to …

Visual learning depends on both the algorithms and the training material. This essay
considers the natural statistics of infant-and toddler-egocentric vision. These natural training …

The cerebral cortex predicts visual motion to adapt human behavior to surrounding objects
moving in real time. Although the underlying mechanisms are still unknown, predictive …

Highlights•There are many methods in deep learning for learning predictive models of the
world.•Such models can be leveraged to produce behavior via a number of planning …

Despite being the workhorse of deep learning, the backpropagation algorithm is no
panacea. It enforces sequential layer updates, thus preventing efficient parallelization of the …

The traditional goal of quantitative analytics is to find simple, transparent models that
generate explainable insights. In recent years, large-scale data acquisition enabled, for …

Neural networks in the brain are dominated by sometimes more than 60% feedback
connections, which most often have small synaptic weights. Different from this, little is known …

One of the main challenges in machine vision relates to the problem of obtaining robust
representation of visual features that remain unaffected by geometric transformations. This …

Event-related potentials (ERPs) provide a window into how the brain is processing
language. Here, we propose a theory that argues that ERPs such as the N400 and P600 …