arXiv subjects

Giorgio A. Ascoli

Publications and source records attributed to Giorgio A. Ascoli.

7 recordsLinked to original sources

arXiv2026

A Voltage-controlled MTJ-CMOS Neuron Emulating Tunable Izhikevich-Inspired Dynamics

Biological neurons exhibit diverse firing dynamics that enable adaptive and stimulus-dependent signalling, yet reproducing these dynamics in hardware has remained an enduring challenge. In this work, we present an Izhikevich- inspired reconfigurable neuron that co-designs voltage-controlled magnetic tunnel junction (V-MTJ) dynamics with CMOS circuitry. The proposed architecture combines V-MTJ excitability dynamics, enabled by a tunable energy landscape, with CMOS recovery dynamics to generate five distinct neuronal firing pat- terns with different spiking, bursting and response characteristics. Our results, based on measured V-MTJ characteristics and circuit simulations using com- mercial GlobalFoundries 22-nm FD-SOI CMOS technology, show an average energy consumption of 145.44 fJ per spike. Algorithmic simulations further show that these firing dynamics reduce inference spike activity by up to 88.6% while maintaining baseline classification accuracy. These results highlight the potential of V-MTJ/CMOS reconfigurable neurons to reduce computational activity and enable compact, energy-efficient brain-inspired computing systems.

cs.ET↗

arXiv2026

Scaled Hippocampus-inspired Neural Networks on Neuromorphic Memristive Hardware

The hippocampus, a key brain region for learning and memory, exhibits rich structural diversity, sparse communication, and robust dynamics with incredible energy efficiency. It offers promising insights for novel computing capabilities, particularly when co-designed with emerging hardware technologies. In this work, we draw inspiration from the rodent CA3 hippocampal subregion to develop the first spiking neural network with neuronal diversity and biologically-realistic resting state dynamics demonstrated on memristor hardware. We propose a network downscaling methodology utilizing a 4-prong objective function and demonstrate a small-scale CA3-inspired network with 179 Izhikevich-modeled neurons, 3 neuronal types and 17,996 synapses with similar resting-state dynamics as the orders-of-magnitude larger full-scale network. The small-scale network is mapped to an FPGA/memristor platform using a greedy algorithm and 18,316 memristors. Benefiting from memristor noise, the hardware implementation shows continuous periodic behavior, outperforming simulated hardware. This work showcases the potential of biologically-realistic algorithms on emerging hardware for neuromorphic computing.

cs.NE↗

arXiv2024

Biologically-Informed Excitatory and Inhibitory Balance for Robust Spiking Neural Network Training

Spiking neural networks drawing inspiration from biological constraints of the brain promise an energy-efficient paradigm for artificial intelligence. However, challenges exist in identifying guiding principles to train these networks in a robust fashion. In addition, training becomes an even more difficult problem when incorporating biological constraints of excitatory and inhibitory connections. In this work, we identify several key factors, such as low initial firing rates and diverse inhibitory spiking patterns, that determine the overall ability to train spiking networks with various ratios of excitatory to inhibitory neurons on AI-relevant datasets. The results indicate networks with the biologically realistic 80:20 excitatory:inhibitory balance can reliably train at low activity levels and in noisy environments. Additionally, the Van Rossum distance, a measure of spike train synchrony, provides insight into the importance of inhibitory neurons to increase network robustness to noise. This work supports further biologically-informed large-scale networks and energy efficient hardware implementations.

cs.NE↗

arXiv2024

A Novel Method for Clustering Cellular Data to Improve Classification

Many fields, such as neuroscience, are experiencing the vast proliferation of cellular data, underscoring the need for organizing and interpreting large datasets. A popular approach partitions data into manageable subsets via hierarchical clustering, but objective methods to determine the appropriate classification granularity are missing. We recently introduced a technique to systematically identify when to stop subdividing clusters based on the fundamental principle that cells must differ more between than within clusters. Here we present the corresponding protocol to classify cellular datasets by combining data-driven unsupervised hierarchical clustering with statistical testing. These general-purpose functions are applicable to any cellular dataset that can be organized as two-dimensional matrices of numerical values, including molecular, physiological, and anatomical datasets. We demonstrate the protocol using cellular data from the Janelia MouseLight project to characterize morphological aspects of neurons.

q-bio.QM↗

arXiv2021

BEAN: Interpretable Representation Learning with Biologically-Enhanced Artificial Neuronal Assembly Regularization

Deep neural networks (DNNs) are known for extracting useful information from large amounts of data. However, the representations learned in DNNs are typically hard to interpret, especially in dense layers. One crucial issue of the classical DNN model such as multilayer perceptron (MLP) is that neurons in the same layer of DNNs are conditionally independent of each other, which makes co-training and emergence of higher modularity difficult. In contrast to DNNs, biological neurons in mammalian brains display substantial dependency patterns. Specifically, biological neural networks encode representations by so-called neuronal assemblies: groups of neurons interconnected by strong synaptic interactions and sharing joint semantic content. The resulting population coding is essential for human cognitive and mnemonic processes. Here, we propose a novel Biologically Enhanced Artificial Neuronal assembly (BEAN) regularization to model neuronal correlations and dependencies, inspired by cell assembly theory from neuroscience. Experimental results show that BEAN enables the formation of interpretable neuronal functional clusters and consequently promotes a sparse, memory/computation-efficient network without loss of model performance. Moreover, our few-shot learning experiments demonstrate that BEAN could also enhance the generalizability of the model when training samples are extremely limited.

cs.NE↗

arXiv2021

Schematic Memory Persistence and Transience for Efficient and Robust Continual Learning

Continual learning is considered a promising step towards next-generation Artificial Intelligence (AI), where deep neural networks (DNNs) make decisions by continuously learning a sequence of different tasks akin to human learning processes. It is still quite primitive, with existing works focusing primarily on avoiding (catastrophic) forgetting. However, since forgetting is inevitable given bounded memory and unbounded task loads, 'how to reasonably forget' is a problem continual learning must address in order to reduce the performance gap between AIs and humans, in terms of 1) memory efficiency, 2) generalizability, and 3) robustness when dealing with noisy data. To address this, we propose a novel ScheMAtic memory peRsistence and Transience (SMART) framework for continual learning with external memory that builds on recent advances in neuroscience. The efficiency and generalizability are enhanced by a novel long-term forgetting mechanism and schematic memory, using sparsity and 'backward positive transfer' constraints with theoretical guarantees on the error bound. Robust enhancement is achieved using a novel short-term forgetting mechanism inspired by background information-gated learning. Finally, an extensive experimental analysis on both benchmark and real-world datasets demonstrates the effectiveness and efficiency of our model.

cs.LG↗

arXiv2006

Some Variations on Maxwell's Equations

In the first sections of this article, we discuss two variations on Maxwell's equations that have been introduced in earlier work--a class of nonlinear Maxwell theories with well-defined Galilean limits (and correspondingly generalized Yang-Mills equations), and a linear modification motivated by the coupling of the electromagnetic potential with a certain nonlinear Schroedinger equation. In the final section, revisiting an old idea of Lorentz, we write Maxwell's equations for a theory in which the electrostatic force of repulsion between like charges differs fundamentally in magnitude from the electrostatic force of attraction between unlike charges. We elaborate on Lorentz' description by means of electric and magnetic field strengths, whose governing equations separate into two fully relativistic Maxwell systems--one describing ordinary electromagnetism, and the other describing a universally attractive or repulsive long-range force. If such a force cannot be ruled out {\it a priori} by known physical principles, its magnitude should be determined or bounded experimentally. Were it to exist, interesting possibilities go beyond Lorentz' early conjecture of a relation to (Newtonian) gravity.

physics.class-ph↗