Topic: recurrent network

Behavioural feedback is critical for learning in the cerebral cortex, but such feedback is often not readily available which slows down learning. Inspired by deep learning algorithms, we introduce a systems-level computational model of cerebro-cerebellar interactions in which a cerebral recurrent network receives continuous cerebral feedback predictions from a cerebellar network, thereby decoupling learning in cerebral networks from future feedback. When trained in a simple sensorimotor task the model shows faster learning and reduced ataxia-like behaviours, in line with experimental observati

In the human brain, some individual neurons respond selectively to abstract variables, invariant to sensory grounding (Mansouri, Freedman, & Buckley, 2020). Similarly tuned units also appear in artificial networks trained on cognitive tasks (Goh et al., 2021). It is often implicitly assumed that the emergence of such interpretable neurons plays a key role in the behavior of the trained network. Here we show that this is not necessarily the case. We train a biologically inspired artificial agent comprising two key components—a recurrent network and an associative memory—on a canonical rule

I will build from Niccolo's discussion of the Blockhead argument to argue that having an FeedForward Network (FN) responding like an recurrent network (RN) in a consciousness experiment is not enough to convince us the two are the same with regards to the posession of mental states and conscious experience. I will then argue that a robust functional equivalence between FFN and RN is akso not supported by the mathematical work on the Universal Approximator theorem, and is also unlikely to hold, as a conjecture, given data in cognitive neuroscience; I will argue that an equivalence of RN and FFN

Gradient-based optimization powered by the backpropagation algorithm proved to be the pivotal method in the training of non-spiking artificial neural networks. At the same time, spiking neural networks hold the promise for efficient processing of real-world sensory data by communicating using discrete events in continuous time. We derive the backpropagation algorithm for a recurrent network of spiking (leaky integrate-and-fire) neurons with hard thresholds and show that the backward dynamics amount to an event-based backpropagation of errors through time. Our derivation uses the jump condition

Homeostatic plasticity plays a key role in stabilizing neural network activity. But what is its role in neural information processing? We showed analytically how homeostasis changes collective dynamics and consequently information flow - depending on the input to the network. We then studied how input and homeostasis on a recurrent network of LIF neurons impacts information flow and task performance. We showed how we can tune the working point of the network, and found that, contrary to previous assumptions, there is not one optimal working point for a family of tasks, but each task may requir

Different stimuli elicit different transient neural responses in the brain. How is the information represented in the parallel neuronal activity of a neuronal population? We investigate this question in Neuropixel recordings of awake behaving mice by inferring the stimulus class (e.g., visual or tactile) from the activity. To quantify the separability, we use an optimally trained linear readout, which can be understood through the framework of Bayesian inference. We find that separability only depends on three geometric properties of the neuronal population vector, described by cones within th

To successfully inform behavior, cortical circuits must produce consistent patterns of neuronal activity within and across trials that allow for reliable stimulus discrimination. Under this perspective, any response variability appears detrimental to sensory systems as it severely limits stimulus discriminability. Here, we propose a beneficial role of response variability: to facilitate faster learning in feedforward-recurrent networks through a self-stabilizing feedback mechanism. We explore this hypothesis in the framework of learning novel stimulus representations in pre-structured recurren