Inferring nonlinear neuronal computation based on physiologically plausible inputs
The computation represented by a sensory neuron's response to stimuli is constructed from
an array of physiological processes both belonging to that neuron and inherited from its …
an array of physiological processes both belonging to that neuron and inherited from its …
Dynamical flexible inference of nonlinear latent factors and structures in neural population activity
Modelling the spatiotemporal dynamics in the activity of neural populations while also
enabling their flexible inference is hindered by the complexity and noisiness of neural …
enabling their flexible inference is hindered by the complexity and noisiness of neural …
Cognitive computing building block: A versatile and efficient digital neuron model for neurosynaptic cores
Marching along the DARPA SyNAPSE roadmap, IBM unveils a trilogy of innovations towards
the TrueNorth cognitive computing system inspired by the brain's function and efficiency …
the TrueNorth cognitive computing system inspired by the brain's function and efficiency …
Degrees of algorithmic equivalence between the brain and its DNN models
Deep neural networks (DNNs) have become powerful and increasingly ubiquitous tools to
model human cognition, and often produce similar behaviors. For example, with their …
model human cognition, and often produce similar behaviors. For example, with their …
Recurrent neural networks with explicit representation of dynamic latent variables can mimic behavioral patterns in a physical inference task
R Rajalingham, A Piccato, M Jazayeri - Nature Communications, 2022 - nature.com
Primates can richly parse sensory inputs to infer latent information. This ability is
hypothesized to rely on establishing mental models of the external world and running mental …
hypothesized to rely on establishing mental models of the external world and running mental …
Deep learning incorporating biologically inspired neural dynamics and in-memory computing
Spiking neural networks (SNNs) incorporating biologically plausible neurons hold great
promise because of their unique temporal dynamics and energy efficiency. However, SNNs …
promise because of their unique temporal dynamics and energy efficiency. However, SNNs …
Understanding and mitigating noise in trained deep neural networks
Deep neural networks unlocked a vast range of new applications by solving tasks of which
many were previously deemed as reserved to higher human intelligence. One of the …
many were previously deemed as reserved to higher human intelligence. One of the …
Neural networks with physics-informed architectures and constraints for dynamical systems modeling
Effective inclusion of physics-based knowledge into deep neural network models of
dynamical systems can greatly improve data efficiency and generalization. Such a priori …
dynamical systems can greatly improve data efficiency and generalization. Such a priori …
Designing neural networks through neuroevolution
Much of recent machine learning has focused on deep learning, in which neural network
weights are trained through variants of stochastic gradient descent. An alternative approach …
weights are trained through variants of stochastic gradient descent. An alternative approach …
Inception loops discover what excites neurons most using deep predictive models
Finding sensory stimuli that drive neurons optimally is central to understanding information
processing in the brain. However, optimizing sensory input is difficult due to the …
processing in the brain. However, optimizing sensory input is difficult due to the …