Advanced Memory and Neural Computing

A Closer-to-Brain Heterosynaptic Learning Rule for Spatiotemporal Spike Pattern Detection with Low-Resolution Synapse

This paper proposes a brain-like learning rule that improves spatiotemporal spike pattern detection with low-resolution synapses by incorporating heterosynaptic plasticity.

SNNs Are Not Transformers (Yet): The Architectural Problems for SNNs in Modeling Long-Range Dependencies

This paper analyzes the limitations of spiking neural networks (SNNs) in modeling long-range dependencies, showing their quadratic sample complexity compared to Transformers and RNNs.

BrainScale: Enabling Scalable Online Learning in Spiking Neural Networks

The paper introduces BrainScale, a system for scalable online learning in spiking neural networks, demonstrating its ability to train large-scale brain models with low memory and high efficiency.

Sustainable Memristors from Shiitake Mycelium for High-Frequency Bioelectronics

This paper demonstrates fungal memristors made from shiitake mycelium that can be grown, trained, and preserved, functioning at up to 6 kHz for neuromorphic computing applications.

Biologically Realistic Computational Primitives of Neocortex Implemented on Neuromorphic Hardware Improve Vision Transformer Performance

The paper implements biologically realistic neocortical circuit motifs on neuromorphic hardware to improve Vision Transformer performance in digit classification.

Stable recurrent dynamics in heterogeneous neuromorphic computing systems using excitatory and inhibitory plasticity

This paper demonstrates a learning rule for neuromorphic systems that balances excitation and inhibition, enabling robust self-sustained dynamics despite device variability.

Spiking Neuron-Astrocyte Networks for Image Recognition

This paper introduces a Spiking Neuron-Astrocyte Network (SNAN) model for image recognition, showing improved performance through astrocyte-mediated modulation of neural connections.

A Burst-Dependent Algorithm for Neuromorphic On-Chip Learning of Spiking Neural Networks

This paper introduces and evaluates Burstprop, a burst-dependent algorithm for spiking neural networks, showing its effectiveness in image classification and robustness to feedback connectivity and weight discretization.

Hyper-Flexible Neural Networks: Rapidly Switching between Logic Operations in a Compact 4-Neuron Circuit

This paper demonstrates a 4-neuron circuit that can rapidly switch between 24 logical functions using fixed synaptic weights, applicable to various neuronal architectures and activation functions.

LoCS-Net: Localizing Convolutional Spiking Neural Network for Fast Visual Place Recognition

The paper introduces LoCS-Net, a convolutional spiking neural network for visual place recognition that outperforms state-of-the-art methods in efficiency and accuracy.

Artificial cerebellum on FPGA: Realistic real-time cerebellar spiking neural network model capable of real-world adaptive motor control

Burstprop for Learning in Spiking Neuromorphic Hardware

This paper adapts the Burstprop algorithm for training hierarchical SNNs on MNIST, showing improved performance over STDP but lower accuracy than BPTT.

Brain-inspired methods for achieving robust computation inheterogeneous mixed-signal neuromorphic processing systems

The paper presents brain-inspired strategies to improve reliability and robustness in neuromorphic systems by leveraging biological constraints and neural coding strategies.

Markov Chain Abstractions of Electrochemical Reaction-Diffusion in Synaptic Transmission for Neuromorphic Computing

The paper abstracts a detailed 3D reaction-diffusion model of a chemical synapse into a compact state space for neuromorphic hardware emulation with preserved input-output dynamics.

A neuromorphic model of olfactory processing and sparse coding in the Drosophila larva brain

This paper develops a neuromorphic model of olfactory processing in Drosophila larvae, showing how sparse coding and efficient encoding can be achieved through feedback inhibition and spike frequency adaptation in a small neural network.

Accurate and efficient time-domain classification with adaptive spiking recurrent neural networks

This paper introduces adaptive spiking recurrent neural networks with a novel surrogate gradient, achieving state-of-the-art performance in time-domain tasks and improved computational efficiency.

Neurogrid simulates cortical cell-types, active dendrites, and top-down attention

Neurogrid simulates cortical models across multiple levels, revealing active dendrites mediate top-down attention.

Real-time detection of bursts in neuronal cultures using a Neuromorphic Auditory Sensor and Spiking Neural Networks

This paper proposes a neuromorphic system for real-time burst detection in neuronal cultures, achieving comparable performance to conventional methods with lower power and latency.

Integrating Non-Spiking Interneurons in Spiking Neural Networks

This paper combines spiking and non-spiking neurons to create a sensorimotor pathway that shapes network output based on analog input, validated through simulation.

The remarkable robustness of surrogate gradient learning for instilling complex function in spiking neural networks

This paper investigates how surrogate gradient learning performs in spiking neural networks, showing its robustness to different surrogate derivatives and the importance of regularization for effective learning.

A solution to the learning dilemma for recurrent networks of spiking neurons

This paper introduces a new learning method for spiking neural networks that enables biologically plausible online learning through gradient descent, achieving performance comparable to BPTT.

A Spiking Neuron and Population Model based on the Growth Transform Dynamical System

This paper introduces a spiking neuron and population model based on Growth Transform dynamical systems, enabling independent control of neurodynamical properties and efficient spiking associative memory.

Back-propagation learning in deep Spike-By-Spike networks

This paper develops a learning rule for deep Spike-by-Spike networks and demonstrates its effectiveness on MNIST classification with 99.3% accuracy.