Related papers: Fast learning synapses with molecular spin valves …
Learning synaptic weights of spiking neural network (SNN) models that can reproduce target spike trains from provided neural firing data is a central problem in computational neuroscience and spike-based computing. The discovery of the…
The brain prepares for learning even before interacting with the environment, by refining and optimizing its structures through spontaneous neural activity that resembles random noise. However, the mechanism of such a process has yet to be…
Quantum-information-inspired experiments in nuclear magnetic resonance spectroscopy may yield a pathway towards determining molecular structure and properties that are otherwise challenging to learn. We measure out-of-time-ordered…
Nanomagnets driven by spin currents provide a natural implementation for a neuron and a synapse: currents allow convenient summation of multiple inputs, while the magnet provides the threshold function. The objective of this paper is to…
The adaptive changes in synaptic efficacy that occur between spiking neurons have been demonstrated to play a critical role in learning for biological neural networks. Despite this source of inspiration, many learning focused applications…
Artificial neural networks encounter a notable challenge known as continual learning, which involves acquiring knowledge of multiple tasks over an extended period. This challenge arises due to the tendency of previously learned weights to…
Binary stochastic neurons (BSNs) are excellent activators for machine learning. An ideal platform for implementing them are low- or zero-energy-barrier nanomagnets (LBMs) possessing in-plane anisotropy (e.g. circular or slightly elliptical…
The appealing feature of molecular electronics is the possibility of exploiting functionality built within a single molecule. This functionality can be employed, for example, for sensing or switching purposes. Thus, ideally, the associated…
In this work, we simulate the functionality of artificial neuron and synapse using spin-orbit torque-based spintronic devices and implemented a fully connected artificial neural netwrok (ANN). These neuro-synaptic devices are emulated using…
Continual learning algorithms strive to acquire new knowledge while preserving prior information. Often, these algorithms emphasise stability and restrict network updates upon learning new tasks. In many cases, such restrictions come at a…
We present a design-scheme for ultra-low power neuromorphic hardware using emerging spin-devices. We propose device models for 'neuron', based on lateral spin valves and domain wall magnets that can operate at ultra-low terminal voltage of…
Detailed understanding of spin dynamics in magnetic nanomaterials is necessary for developing ultrafast, low-energy and high-density spintronic logic and memory. Here, we develop micromagnetic models and analytical solutions to elucidate…
Brain-inspired computing architectures attempt to emulate the computations performed in the neurons and the synapses in human brain. Memristors with continuously tunable resistances are ideal building blocks for artificial synapses. Through…
The brain, which uses redundancy and continuous learning to overcome the unreliability of its components, provides a promising path to building computing systems that are robust to the unreliability of their constituent nanodevices. In this…
How neurons integrate the myriad synaptic inputs scattered across their dendrites is a fundamental question in neuroscience. Multiple neurophysiological experiments have shown that dendritic non-linearities can have a strong influence on…
The weight matrix (WM) of a neural network (NN) is its program. The programs of many traditional NNs are learned through gradient descent in some error function, then remain fixed. The WM of a self-referential NN, however, can keep rapidly…
Precise spike timing as a means to encode information in neural networks is biologically supported, and is advantageous over frequency-based codes by processing input features on a much shorter time-scale. For these reasons, much recent…
We present a new class of control pulses designed to transfer co-located ensembles without relying on frequency selectivity, thereby allowing much faster state-transitions. A geometric approach allows us to construct sequences which are…
The brain modifies its synaptic strengths during learning in order to better adapt to its environment. However, the underlying plasticity rules that govern learning are unknown. Many proposals have been suggested, including Hebbian…
Machine Learning finds application in the quantum control and readout of qubits. In this work we apply Artificial Neural Networks to assist the manipulation and the readout of a prototypical molecular spin qubit - an Oxovanadium(IV) moiety…