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.
Paper introduces supervised and unsupervised TAM models for binary neurons.
The study reveals how synaptic correlations promote dimension reduction in neural networks.
Biological neurons learn tensor decompositions of higher-order correlations using nonlinear Hebbian plasticity.
Neural network models of early sensory processing typically reduce the dimensionality of streaming input data. Such networks learn the principal subspace, in the sense of principal component analysis (PCA), by adjusting synaptic weights according to activity-dependent learning rules. When derived from a principled cost…
Neural networks are commonly trained to make predictions through learning algorithms. Contrastive Hebbian learning, which is a powerful rule inspired by gradient backpropagation, is based on Hebb's rule and the contrastive divergence algorithm. It operates in two phases, the forward (or free) phase, where the data are …
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 …
Despite our extensive knowledge of biophysical properties of neurons, there is no commonly accepted algorithmic theory of neuronal function. Here we explore the hypothesis that single-layer neuronal networks perform online symmetric nonnegative matrix factorization (SNMF) of the similarity matrix of the streamed 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…
In this paper, we derive a new model of synaptic plasticity, based on recent algorithms for reinforcement learning (in which an agent attempts to learn appropriate actions to maximize its long-term average reward). We show that these direct reinforcement learning algorithms also give locally optimal performance for the…
Sleep-based regularization stabilizes STDP in recurrent neural networks.
Biological neural network mimics CCA for multi-channel data.
A model retains learned knowledge for longer by adding a plastic component to neural networks.
Analyzes unsupervised neural networks using statistical mechanics and Monte Carlo simulations.
Study on neural networks with non-normal interactions reveals unique spectral properties.
Paper models Pavlov's classical conditioning using stochastic processes and Langevin equations.
Bio-inspired neural networks use predictive coding for efficient weight updates.
BDH model learns like the brain, rivaling Transformer performance.
New learning rules from information bottleneck improve deep learning without precise labels.
Natural gradient learning improves synaptic plasticity in spiking neurons.
Identifies learning rules from neural network observables.
New algorithm shows neural networks can learn without full backpropagation.
Dense neural networks learn efficiently with large datasets and noise.
How can we build agents that keep learning from experience, quickly and efficiently, after their initial training? Here we take inspiration from the main mechanism of learning in biological brains: synaptic plasticity, carefully tuned by evolution to produce efficient lifelong learning. We show that plasticity, just li…
Unified approach for neural networks with multi-compartmental neurons and non-Hebbian plasticity.
In this work we propose Hebbian-descent as a biologically plausible learning rule for hetero-associative as well as auto-associative learning in single layer artificial neural networks. It can be used as a replacement for gradient descent as well as Hebbian learning, in particular in online learning, as it inherits the…
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…
Oja's rule improves neural network training without engineered tricks.
In a physical neural system, where storage and processing are intimately intertwined, the rules for adjusting the synaptic weights can only depend on variables that are available locally, such as the activity of the pre- and post-synaptic neurons, resulting in local learning rules. A systematic framework for studying t…
Hebbian learning derived from maximum entropy principles.
This paper presents a new neural architecture that combines a modulated Hebbian network (MOHN) with DQN, which we call modulated Hebbian plus Q network architecture (MOHQA). The hypothesis is that such a combination allows MOHQA to solve difficult partially observable Markov decision process (POMDP) problems which impa…
Brain uses synaptic failure to sample from posterior distributions.
Artifical Neural Networks are a particular class of learning systems modeled after biological neural functions with an interesting penchant for Hebbian learning, that is "neurons that wire together, fire together". However, unlike their natural counterparts, artificial neural networks have a close and stringent couplin…
We consider the inverse Ising problem, i.e. the inference of network couplings from observed spin trajectories for a model with continuous time Glauber dynamics. By introducing two sets of auxiliary latent random variables we render the likelihood into a form, which allows for simple iterative inference algorithms with…
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…
Locally learned synaptic failure enables complete Bayesian inference.
We propose a new cognitive framework for option price modelling, using quantum neural computation formalism. Briefly, when we apply a classical nonlinear neural-network learning to a linear quantum Schrödinger equation, as a result we get a nonlinear Schrödinger equation (NLS), performing as a quantum stochastic filter…
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…
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…
We unify recent neural approaches to one-shot learning with older ideas of associative memory in a model for metalearning. Our model learns jointly to represent data and to bind class labels to representations in a single shot. It builds representations via slow weights, learned across tasks through SGD, while fast wei…
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…
Proposes a new neural network approach to credit assignment.
Enhanced BCPNN learns hidden representations without labels.
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…
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…
New model reveals balance crucial for robust neural coding.
Machine learning (ML) classifiers always benefit from more informative input features. We seek to auto-generate stronger feature sets in order to address the difficulty that ML methods often experience given limited training data. A wide range of biological neural nets (BNNs) excel at fast learning, implying that they …