Related papers: Fast learning synapses with molecular spin valves …
Memristive devices represent a promising technology for building neuromorphic electronic systems. In addition to their compactness and non-volatility features, they are characterized by computationally relevant physical properties, such as…
Longitudinal coupling offers a compelling pathway for quantum nondemolition (QND) readout, but pulse design is constrained by hardware limitations such as the coupling strength and the photon number required to stay within the linear…
In this paper, we propose a data-adaptive non-parametric kernel learning framework in margin based kernel methods. In model formulation, given an initial kernel matrix, a data-adaptive matrix with two constraints is imposed in an entry-wise…
We present an account of neuroplasticity with respect to cell-internal processing pathways in relation to membrane and synaptic plasticity. We think traditional synapse-centric, weight-based models of memorization are not sufficient or…
Formation of a magnetic hysteresis loop with respect to a bias voltage is investigated theoretically in a spin-valve device based on a single magnetic molecule. We consider a device consisting of two ferromagnetic electrodes bridged by a…
Reducing energy dissipation while increasing speed in computation and memory is a long-standing challenge for spintronics research. In the last 20 years, femtosecond lasers have emerged as a tool to control the magnetization in specific…
Magnetization switching due to a current-pulse in symmetric and asymmetric spin valves is studied theoretically within the macrospin model. The switching process and the corresponding switching parameters are shown to depend significantly…
The deployment of AI on edge computing devices faces significant challenges related to energy consumption and functionality. These devices could greatly benefit from brain-inspired learning mechanisms, allowing for real-time adaptation…
High order momentum-based parameter update algorithms have seen widespread applications in training machine learning models. Recently, connections with variational approaches have led to the derivation of new learning algorithms with…
Recent trends in the field of neural network accelerators investigate weight quantization as a means to increase the resource- and power-efficiency of hardware devices. As full on-chip weight storage is necessary to avoid the high energy…
Neuronal spikes directly drive muscles and endow animals with agile movements, but applying the spike-based control signals to actuators in artificial sensor-motor systems inevitably causes a collapse of learning. We developed a system that…
We show that the established physics of spin valves together with the recently discovered giant spin-Hall effect could be used to construct Read and Write units that can be integrated into a single spin switch with input-output isolation,…
In this paper, we propose a machine learning model, which dynamically changes the features during training. Our main motivation is to update the model in a small content during the training process with replacing less descriptive features…
Machine-learning tasks performed by neural networks demonstrated useful capabilities for producing reliable, and repeatable intelligent decisions. Integrated photonics, leveraging both component miniaturization and the wave-nature of the…
This paper presents a learning-based control strategy for non-linear throttle valves with an asymmetric hysteresis, leading to a near-optimal controller without requiring any prior knowledge about the environment. We start with a carefully…
We numerically demonstrate a network of coupled oscillators that can learn to solve a classification task from a set of examples -- performing both training and inference through the nonlinear evolution of the system. We accomplish this by…
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…
We demonstrate that extremely low resolution quantized (nominally 5-state) synapses with large stochastic variations in Domain Wall (DW) position can be both energy efficient and achieve reasonably high testing accuracies compared to Deep…
The ability of a brain or a neural network to efficiently learn depends crucially on both the task structure and the learning rule. Previous works have analyzed the dynamical equations describing learning in the relatively simplified…
This paper is a study of reinforcement learning (RL) as an optimal-control strategy for control of nonlinear valves. It is evaluated against the PID (proportional-integral-derivative) strategy, using a unified framework. RL is an autonomous…