[HTML][HTML] Opportunities for neuromorphic computing algorithms and applications

CD Schuman, SR Kulkarni, M Parsa… - Nature Computational …, 2022 - nature.com
Neuromorphic computing technologies will be important for the future of computing, but
much of the work in neuromorphic computing has focused on hardware development. Here …

Believing in dopamine

SJ Gershman, N Uchida - Nature Reviews Neuroscience, 2019 - nature.com
Midbrain dopamine signals are widely thought to report reward prediction errors that drive
learning in the basal ganglia. However, dopamine has also been implicated in various …

Building machines that learn and think like people

BM Lake, TD Ullman, JB Tenenbaum… - Behavioral and brain …, 2017 - cambridge.org
Recent progress in artificial intelligence has renewed interest in building systems that learn
and think like people. Many advances have come from using deep neural networks trained …

Stochastic phase-change neurons

T Tuma, A Pantazi, M Le Gallo, A Sebastian… - Nature …, 2016 - nature.com
Artificial neuromorphic systems based on populations of spiking neurons are an
indispensable tool in understanding the human brain and in constructing neuromimetic …

Towards biologically plausible deep learning

Y Bengio, DH Lee, J Bornschein, T Mesnard… - arXiv preprint arXiv …, 2015 - arxiv.org
Neuroscientists have long criticised deep learning algorithms as incompatible with current
knowledge of neurobiology. We explore more biologically plausible versions of deep …

Integration of nanoscale memristor synapses in neuromorphic computing architectures

G Indiveri, B Linares-Barranco, R Legenstein… - …, 2013 - iopscience.iop.org
Conventional neuro-computing architectures and artificial neural networks have often been
developed with no or loose connections to neuroscience. As a consequence, they have …

Fully complex-valued dendritic neuron model

S Gao, MC Zhou, Z Wang, D Sugiyama… - IEEE transactions on …, 2021 - ieeexplore.ieee.org
A single dendritic neuron model (DNM) that owns the nonlinear information processing
ability of dendrites has been widely used for classification and prediction. Complex-valued …

Bayesian computation emerges in generic cortical microcircuits through spike-timing-dependent plasticity

B Nessler, M Pfeiffer, L Buesing… - PLoS computational …, 2013 - journals.plos.org
The principles by which networks of neurons compute, and how spike-timing dependent
plasticity (STDP) of synaptic weights generates and maintains their computational function …

Perceptual decision-making as probabilistic inference by neural sampling

RM Haefner, P Berkes, J Fiser - Neuron, 2016 - cell.com
We address two main challenges facing systems neuroscience today: understanding the
nature and function of cortical feedback between sensory areas and of correlated variability …

Neuronal message passing using Mean-field, Bethe, and Marginal approximations

T Parr, D Markovic, SJ Kiebel, KJ Friston - Scientific reports, 2019 - nature.com
Neuronal computations rely upon local interactions across synapses. For a neuronal
network to perform inference, it must integrate information from locally computed messages …