Topic: feedforward neural networks

Humans and other animals often perform similar actions in different contexts. For instance, we use different criteria when judging whether an apple or avocado are ripe, but use very similar motor actions to move the fruit into our basket if we select it. We hypothesize that this ability to context switch is facilitated by functional modularity within brain regions, such as the specialization of a subpopulation of inferotemporal cortex neurons for face relative to non-face features. However, the link between this functional modularity and context-dependent behavior is not fully understood. Here

Progress in deep learning has spawned great successes in many engineering applications. As a prime example, convolutional neural networks, a type of feedforward neural networks, are now approaching – and sometimes even surpassing – human accuracy on a variety of visual recognition tasks. In this talk, however, I will show that these neural networks and their recent extensions exhibit a limited ability to solve seemingly simple visual reasoning problems involving incremental grouping, similarity, and spatial relation judgments. Our group has developed a recurrent network model of classical and

Value optimization is a defining principle of economic behavior. To uncover the underlying psychological and neural processes, we developed a behavioral task based on the ‘knapsack problem’. Given several items, each with a value and weight, the objective is to maximize value within the weight limit of the knapsack. Two rhesus monkeys solved a touchscreen-based version that equates weights with juice reward sizes. The animals performed well above chance and achieved at least 75% of the optimal reward value on 80% of all knapsack trials. We defined each unique set of items as an ‘instance,’ and

Sensory systems reliably process incoming stimuli in spite of changes in context. Most recent models accredit this context invariance to an extraction of increasingly complex sensory features in hierarchical feedforward networks. Here, we study how context-invariant representations can be established by feedback rather than feedforward processing. We show that feedforward neural networks modulated by feedback can dynamically generate invariant sensory representations. The required feedback can be implemented as a slow and spatially diffuse gain modulation. The invariance is not present on the