arXiv research

ANPyC combats forgetting by pruning and consolidating neural parameters.

Paper benchmarks CF mitigation in federated time series forecasting.

Sleep-based regularization stabilizes STDP in recurrent neural networks.

A model retains learned knowledge for longer by adding a plastic component to neural networks.

Brain uses synaptic failure to sample from posterior distributions.

Synaptic strength can be seen as probability to propagate impulse, and according to synaptic plasticity, function could exist from propagation activity to synaptic strength. If the function satisfies constraints such as continuity and monotonicity, neural network under external stimulus will always go to fixed point, a…

Convolutional Neural Networks(CNNs) are both computation and memory intensive which hindered their deployment in mobile devices. Inspired by the relevant concept in neural science literature, we propose Synaptic Pruning: a data-driven method to prune connections between input and output feature maps with a newly propos…

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

Locally learned synaptic failure enables complete Bayesian inference.

New synaptic model derived from reinforcement learning for spiking neurons.

Learning and memory in the brain are implemented by complex, time-varying changes in neural circuitry. The computational rules according to which synaptic weights change over time are the subject of much research, and are not precisely understood. Until recently, limitations in experimental methods have made it challen…

Natural gradient learning improves synaptic plasticity in spiking neurons.

There has been significant recent interest towards achieving highly efficient deep neural network architectures. A promising paradigm for achieving this is the concept of evolutionary deep intelligence, which attempts to mimic biological evolution processes to synthesize highly-efficient deep neural networks over succe…

A promising paradigm for achieving highly efficient deep neural networks is the idea of evolutionary deep intelligence, which mimics biological evolution processes to progressively synthesize more efficient networks. A crucial design factor in evolutionary deep intelligence is the genetic encoding scheme used to simula…

Enhances SNNs for spatio-temporal feature extraction.

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…

Unified framework for adaptive learning systems using consolidation and expansion operations.

New model reveals balance crucial for robust neural coding.

In this work, we perform an exploratory study on synthesizing deep neural networks using biological synaptic strength distributions, and the potential influence of different distributions on modelling performance particularly for the scenario associated with small data sets. Surprisingly, a CNN with convolutional layer…

EVCL combines VCL and EWC to prevent forgetting new tasks.

EWC helps prevent forgetting in neural networks by adjusting weights dynamically.

The brain optimizes memory by forgetting what's predictable, improving generalization.

Unified understanding of three continual learning regularisation methods.

A new neural model evolves to learn at the synaptic level.

Technological progress is leading to proliferation and diversification of trading venues, thus increasing the relevance of the long-standing question of market fragmentation versus consolidation. To address this issue quantitatively, we analyse systems of adaptive traders that choose where to trade based on their previ…

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 …

This paper suggests a learning-theoretic perspective on how synaptic plasticity benefits global brain functioning. We introduce a model, the selectron, that (i) arises as the fast time constant limit of leaky integrate-and-fire neurons equipped with spiking timing dependent plasticity (STDP) and (ii) is amenable to the…

Dynamics and function of neuronal networks are determined by their synaptic connectivity. Current experimental methods to analyze synaptic network structure on the cellular level, however, cover only small fractions of functional neuronal circuits, typically without a simultaneous record of neuronal spiking activity. H…

Algorithm improves model performance on shifted concepts without retraining.

Collecting the large datasets needed to train deep neural networks can be very difficult, particularly for the many applications for which sharing and pooling data is complicated by practical, ethical, or legal concerns. However, it may be the case that derivative datasets or predictive models developed within individu…

Biological neural network mimics CCA for multi-channel data.

Catastrophic forgetting/interference is a critical problem for lifelong learning machines, which impedes the agents from maintaining their previously learned knowledge while learning new tasks. Neural networks, in particular, suffer plenty from the catastrophic forgetting phenomenon. Recently there has been several eff…

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

A model explains credit assignment in deep learning networks.

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

Bayesian method reconstructs neural network memories from connectivity.

New algorithm finds important synapses without training data.

Dual representations for robust risk measures and uncertainty sets.

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

Elastic weight consolidation (EWC, Kirkpatrick et al, 2017) is a novel algorithm designed to safeguard against catastrophic forgetting in neural networks. EWC can be seen as an approximation to Laplace propagation (Eskin et al, 2004), and this view is consistent with the motivation given by Kirkpatrick et al (2017). In…

Olshausen and Field (OF) proposed that neural computations in the primary visual cortex (V1) can be partially modeled by sparse dictionary learning. By minimizing the regularized representation error they derived an online algorithm, which learns Gabor-filter receptive fields from a natural image ensemble in agreement …

FedFMC improves federated learning on non-iid data without sharing data or increasing communication costs.

Paper uses AI to predict stock market volatility with neural networks and genetic algorithms.

Paper models Pavlov's classical conditioning using stochastic processes and Langevin equations.

Recently a daily routine for associative neural networks has been proposed: the network Hebbian-learns during the awake state (thus behaving as a standard Hopfield model), then, during its sleep state, optimizing information storage, it consolidates pure patterns and removes spurious ones: this forces the synaptic matr…

Identifies learning rules from neural network observables.

Class incremental learning refers to a special multi-class classification task, in which the number of classes is not fixed but is increasing with the continual arrival of new data. Existing researches mainly focused on solving catastrophic forgetting problem in class incremental learning. To this end, however, these m…

Deep neural networks (DNNs) often require good regularizers to generalize well. Currently, state-of-the-art DNN regularization techniques consist in randomly dropping units and/or connections on each iteration of the training algorithm. Dropout and DropConnect are characteristic examples of such regularizers, that are …