Neural Networks and Applications

The paper predicts neural circuit structure across species by optimizing a three-layer neural network to achieve efficient learning, recovering mammalian 3/2 and invertebrate 7/2 scaling laws.

The paper introduces two biologically plausible algorithms for segmenting time series based on underlying dynamics, showing good performance on autoregressive models and voice recordings.

The paper introduces a confidence-controlled Hebbian learning rule that efficiently extracts category membership from optimized stimulus encoding layers, outperforming reward-modulated Hebbian learning.

The paper introduces a recurrent neural network architecture that enables accurate sequence prediction in stochastic and structured environments through gating, lateral connections, and recurrent weight training.

The paper shows how local synaptic pruning rules can optimize global network architecture in a deep Boltzmann machine model of sensory encoding.

This paper explores parallels between normalization strategies in artificial and biological neural networks, arguing for functional equivalence and proposing a new algorithm inspired by synaptic scaling.

The paper uses autoencoder networks to show that regularization can resolve ambiguity in connectivity weights, allowing latent variable extraction through nonlinear dimensionality reduction.

The paper introduces dendritic normalisation to improve learning in sparsely connected neural networks, showing significant performance gains over existing methods.

The paper constructs an Artificial Neurovascular Network (ANVN) to study how training both neural and vascular networks affects performance and energy efficiency.

The paper introduces the gradient clusteron (G-clusteron), a model neuron that uses gradient descent and structural plasticity to solve classification tasks, achieving comparable performance to logistic regression on MNIST.

This study shows that both humans and recurrent neural networks develop aligned neural number lines to generalize magnitude concepts across contexts.

This paper demonstrates that Hebbian learning in threshold-linear associative networks can achieve higher storage capacity than binary networks and surpass theoretical bounds through pattern sparsification.

The paper introduces a new classification framework for time series data using covariance patterns in recurrent neuronal networks, showing it can effectively capture second-order statistical features.

This paper develops a novel RNN architecture, YamRNN, with fewer parameters and faster learning performance compared to LSTM and GRU on sequence classification tasks.

This paper introduces a learning algorithm that achieves high sample efficiency using bio-plausible mechanisms, showing that adaptive tuning curve widths improve both sample efficiency and final precision.

This study examines how classification capacity in deep neural networks improves with hierarchy, showing that changes in object manifold geometry underlie this improvement.

The paper compares evolutionary processes and over-parameterized neural networks, arguing that both use blind fitting to solve complex tasks without explicit representation.

This paper argues that animal learning is not primarily driven by sophisticated algorithms but by innate, structured brain connectivity, suggesting a new direction for improving artificial neural networks.

This paper introduces a biologically plausible learning rule for recurrent neural networks that uses local information and random feedback to train networks for time-dependent tasks.

The paper shows that neural circuits have an optimal size for learning performance, where larger circuits can either enhance complex behaviors or improve learning of simpler tasks, but beyond a point, increased size impairs learning due to noise.

This paper discusses how deep neural networks can model neural responses and cognitive functions, highlighting their accuracy and potential in computational neuroscience.

This paper proposes recurrent attractor neural networks with sparse connectivity to overcome classification limitations in feed-forward networks with limited neuron connections.

This paper shows that a predictive coding network with local Hebbian plasticity can approximate error back-propagation for supervised learning without external control.