Related papers: Adiabatic Superconducting Artificial Neural Networ…
We present a new study of magnetic structures with controllable effective exchange energy for Josephson switches and memory. As a basis for a weak link we propose to use a periodic structure comprised of ferromagnetic (F) layers spaced by…
In this letter, we present an implementation of a neural microcircuit for image processing employing Hebbian-adaptive learning. The neuronal circuit utilizes only excitatory synapses to correlate action potentials, extracting the…
We investigate the efficient transmission and processing of weak, subthreshold signals in a realistic neural medium in the presence of different levels of the underlying noise. Assuming Hebbian weights for maximal synaptic conductances --…
Multilayer perceptron (MLP) is a class of networks composed of multiple layers of perceptrons, and it is essentially a mathematical function. Based on MLP, we develop a new numerical method to find the extrema of functionals. As…
Networks of superconducting optoelectronic neurons are investigated for their near-term technological potential and long-term physical limitations. Networks with short average path length, high clustering coefficient, and power-law degree…
In this paper, we present SIMAP, a novel layer integrated into deep learning models, aimed at enhancing the interpretability of the output. The SIMAP layer is an enhanced version of Simplicial-Map Neural Networks (SMNNs), an explainable…
Superconductor electronics (SCE) is competing to become a platform for efficient implementations of neuromorphic computing and deep learning algorithms (DLAs) with projects mostly concentrating on searching for gates that would better mimic…
Magnetic flux quantization in superconductors allows the implementation of fast and energy-efficient digital superconducting circuits. However, the information representation in magnetic flux severely limits their functional density…
We describe an approximation to backpropagation algorithm for training deep neural networks, which is designed to work with synapses implemented with memristors. The key idea is to represent the values of both the input signal and the…
While deep learning has led to remarkable advances across diverse applications, it struggles in domains where the data distribution changes over the course of learning. In stark contrast, biological neural networks continually adapt to…
This paper proposes an improved design of the perceptron unit to mitigate the vanishing gradient problem. This nuisance appears when training deep multilayer perceptron networks with bounded activation functions. The new neuron design,…
Superconductor electronics (SCE) appear promising for low energy applications. However, the achieved and projected circuit densities are insufficient for direct competition with CMOS technology. Original algorithms and nontraditional…
A closed-form solution exists in two-class linear discriminant analysis (LDA), which discriminates two Gaussian-distributed classes in a multi-dimensional feature space. In this work, we interpret the multilayer perceptron (MLP) as a…
This paper introduces the Modular Neural Computer (MNC), a memory-augmented neural architecture for exact algorithmic computation on variable-length inputs. The model combines an external associative memory of scalar cells, explicit read…
Mean-field models provide a link between microscopic neuronal activity and macroscopic brain dynamics. Their derivation depends on simplifying assumptions, such as all-to-all connectivity, limiting their biological realism. To overcome…
Correlated electrical activity in neurons is a prominent characteristic of cortical microcircuits. Despite a growing amount of evidence concerning both spike-count and subthreshold membrane potential pairwise correlations, little is known…
Neuromorphic Computing (NC), which emulates neural activities of the human brain, is considered for low-power implementation of artificial intelligence. Towards realizing NC, fabrication, and investigations of hardware elements such as…
In neuromorphic computing, artificial synapses provide a multi-weight conductance state that is set based on inputs from neurons, analogous to the brain. Additional properties of the synapse beyond multiple weights can be needed, and can…
Hypergraphs are vital in modelling data with higher-order relations containing more than two entities, gaining prominence in machine learning and signal processing. Many hypergraph neural networks leverage message passing over hypergraph…
The human brain functions very differently from artificial neural networks (ANN) and possesses unique features that are absent in ANN. An important one among them is "adaptive synaptogenesis" that modifies synaptic weights when needed to…