Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

169,291 papers · 148 categories

Trend · papers per month

20405979 · Jun 202019922001200920182026
48 results for synaptic response

A neuromorphic unit models complex synapses efficiently.

problem Efficiently simulating complex synaptic response functions in neural networks.
method Digital neuromorphic architecture, Spiking Temporal Processing Unit (STPU), modeling arbitrary complex synaptic response functions.
result Demonstrates flexibility and efficiency of STPU for instantiating neural algorithms.

Balanced excitation and inhibition enhance neuronal selectivity and robustness.

problem Ensuring robust neuronal responses in noisy environments.
method Investigated the conditions for balanced excitation and inhibition to enhance robustness of single neurons and network attractor states.
result Balanced excitation and inhibition are crucial for high-capacity, noise-resistant neuronal selectivity.

Brain uses synaptic failure to sample from posterior distributions.

problem Bayesian inference in the brain's probabilistic computations.
method Adapting synaptic failure to sample posterior predictive distributions.
result Synaptic failure enables sampling of complete posterior predictive distributions.

High-speed model accurately simulates neuromorphic devices.

problem Accurately modeling stochastic synapses in large-scale neuromorphic systems.
method Generative vector autoregressive model based on resistive memory cell data.
result Fast, high-throughput model reproduces synaptic parameters and correlations.

Study shows CNNs can perform well with less data using biological synaptic distributions.

problem Training deep neural networks with limited data.
method Synthesizing CNNs using log-normal or correlated center-surround synaptic strength distributions.
result CNNs with biological synaptic strength distributions can perform well with fewer data samples.

The study reveals how synaptic correlations promote dimension reduction in neural networks.

problem Understanding how synaptic correlations affect neural correlations and dimension reduction in deep neural networks.
method A simplified model of dimension reduction considering pairwise correlations among synapses, using mathematical self-consistency for both binary and continuous synapses.
result Weakly-correlated synapses encourage dimension reduction compared to orthogonal synapses, and they also slow down the decorrelation process.

Synaptic cluster-driven evolution improves deep neural networks by reducing synapses and clusters.

problem Efficiently synthesizing deep neural networks with fewer synapses and clusters.
method Synaptic cluster-driven genetic encoding scheme.
result Significantly smaller number of synapses and clusters in offspring networks.

CNNs accurately model retinal responses to natural scenes.

problem Understanding neural computations in retinal responses to natural stimuli.
method Deep convolutional neural networks (CNNs) were used to model retinal responses to natural scenes.
result CNNs are more accurate than linear models in predicting retinal responses to natural scenes.

Enhances SNNs for spatio-temporal feature extraction.

problem Insufficient temporal dependencies in existing SNN synaptic structures.
method Integrates temporal convolution and attention mechanisms into synaptic connections.
result Improves SNN performance on classification tasks.

Learning in neural networks poses peculiar challenges when using discretized rather then continuous synaptic states. The choice of discrete synapses is motivated by biological reasoning and experiments, and possibly by hardware implementation considerations as well. In this paper we extend a previous large deviations a…

2016-02-12abs ↗pdf ↗

This paper introduces a hierarchical associative memory model with multiple layers.

problem Limitations of traditional associative memory models with only one hidden layer.
method Develops a fully recurrent model with arbitrary layers, including locally connected ones, and a corresponding energy function.
result The model can dynamically assemble memories using weights from lower layers and higher layers' rules.

Bayesian inference for DNN synaptic connectivity improves regularization without manual tuning.

problem Improving deep neural network performance through effective regularization.
method Bayesian inference with Beta priors over binary synaptic variables, using Black-Box Variational inference.
result Effective, heuristics-free network regularization scheme.

ANPyC combats forgetting by pruning and consolidating neural parameters.

problem Catastrophic forgetting in neural networks, especially with long-term tasks.
method Adversarial Neural Pruning and Synaptic Consolidation (ANPyC) to balance task-relevant and irrelevant parameters.
result ANPyC prevents forgetting while enabling efficient learning of multiple tasks.

A neuron is a basic physiological and computational unit of the brain. While much is known about the physiological properties of a neuron, its computational role is poorly understood. Here we propose to view a neuron as a signal processing device that represents the incoming streaming data matrix as a sparse vector of …

2014-05-12abs ↗pdf ↗

New algorithm uses random matrices for neural network training without synaptic weight symmetries.

problem Training neural networks efficiently and without synaptic weight symmetries.
method Contrastive Hebbian learning with random feedback weights.
result Random contrastive Hebbian learning achieves better computational models for learning.

Biological neural network mimics CCA for multi-channel data.

problem Implementing CCA in a biologically plausible neural network.
method Derive an online CCA algorithm with local synaptic updates for multi-compartmental neurons.
result The derived neural network architecture and synaptic updates resemble cortical pyramidal neuron behavior.

Improved KAN model explains brain dynamics through edge learning and synaptic strength.

problem Explaining brain dynamics and frequencies in different brain regions.
method ELKAN (Edge Learning KNN) model with edge learning and trimming, inspired by brain science.
result ELKAN model outperforms KAN in explaining brain frequencies and dynamics.

Elite ONNs learn better with synaptic plasticity, improving performance over CNNs.

problem Limited heterogeneity in ONNs due to fixed operator sets.
method Synaptic plasticity-based search for optimal operator sets.
result Elite ONNs achieve superior learning performance compared to conventional methods.

New framework models neural systems with random architecture on manifolds.

problem Complex, uncertain systems with non-Gaussian outputs.
method Latent random field on compact manifold generates neural architecture and weights.
result Synthetic neural systems can produce stochastic outputs for deterministic inputs.

Analyzes unsupervised neural networks using statistical mechanics and Monte Carlo simulations.

problem Understanding computational capabilities of unsupervised neural networks.
method Statistical mechanics approach and Monte Carlo simulations.
result Obtained a phase diagram summarizing network performance.

Identifies learning rules from neural network observables.

problem Determine the underlying plasticity rules governing learning in biological systems.
method Simulated idealized neuroscience experiments with artificial neural networks to generate a dataset of learning trajectories. Used linear and non-linear classifiers to identify learning rules from aggregate statistics of weights, activations, and activity changes.
result Different classes of learning rules can be separated solely on the basis of aggregate statistics of the weights, activations, or instantaneous layer-wise activity changes.

New method improves deep learning performance without weight symmetry.

problem Challenges in scaling non-symmetric learning methods to deep convolutional networks.
method Introduced techniques to mitigate scalability issues, including a modified feedback alignment method.
result Demonstrated competitive performance with backpropagation using a weaker form of weight symmetry.

New framework boosts neural network performance and resilience.

problem Susceptibility of compact neural network implementations to system disturbances.
method Realistic crossbar simulations and Mosaics framework to re-use synaptic connections.
result Compact neural networks are noise-immune and perform well under disturbances.

Unified theory for training neural networks with binary synapses.

problem Discrete nature of synapses and complex interactions in neural networks.
method Variational mean-field theory decomposing learning into maximization and expectation steps.
result Unified framework for unsupervised learning in neural networks.

Neural networks with learned biases can approximate any function.

problem Whether neural networks with only learned biases can approximate any continuous function.
method Theoretical and numerical analysis of random weights and learned biases in neural networks.
result Feedforward and recurrent neural networks with random weights can approximate any continuous function and dynamical systems.