Related papers: Reconfigurable classifier based on spin torque dri…

The ever-increasing amount of data from ubiquitous smart devices fosters data-centric and cognitive algorithms. Traditional digital computer systems have separate logic and memory units, resulting in a huge delay and energy cost for…

Much of the information the brain processes and stores is temporal in nature - a spoken word or a handwritten signature, for example, is defined by how it unfolds in time. However, it remains unclear how neural circuits encode complex…

Convolutional Neural Networks (CNN) outperform traditional classification methods in many domains. Recently these methods have gained attention in neuroscience and particularly in brain-computer interface (BCI) community. Here, we introduce…

Memory devices operating due to the fast proton transfer (PT) process are proposed by means of the first-principles calculations. Writing an information is performed using the electrostatic potential of the scanning tunneling microscopy…

Automata-logic connections are pillars of the theory of regular languages. Such connections are harder to obtain for transducers, but important results have been obtained recently for word-to-word transformations, showing that the three…

Pre-trained Transformer models like T5 and BART have advanced the state of the art on a wide range of text generation tasks. Compressing these models into smaller ones has become critically important for practical use. Common neural network…

Recent success in natural language processing has motivated growing interest in large-scale foundation models for neuroimaging data. Such models often require discretization of continuous neural time series data, a process referred to as…

Neural Turing Machines (NTMs) are an instance of Memory Augmented Neural Networks, a new class of recurrent neural networks which decouple computation from memory by introducing an external memory unit. NTMs have demonstrated superior…

We propose a new network architecture for standard spin-Hall magnetic tunnel junction-based spintronic neurons that allows them to compute multiple critical convolutional neural network functionalities simultaneously and in parallel, saving…

Neuromorphic computing aims to mimic both the function and structure of biological neural networks to provide artificial intelligence with extreme efficiency. Conventional approaches store synaptic weights in non-volatile memory devices…

This paper describes a numerical experiment of magnetization switching driven by spin-polarized current in high-TMR magnetic tunnel junctions (TMR>100%). Differently from other works, the current density distribution throughout the…

This paper proposes a Convolutional Neural Network (CNN) inspired by Multitask Learning (MTL) and based on speech features trained under the joint supervision of softmax loss and center loss, a powerful metric learning strategy, for the…

Coupled networks of mass-spring resonators have attracted growing attention across multiple fundamental and applied research directions, including reservoir computing for artificial intelligence. This has led to the exploration of platforms…

The increasing need for compact and low-power computing solutions for machine learning applications has triggered significant interest in energy-efficient neuromorphic systems. However, most of these architectures rely on spiking neural…

Low barrier nanomagnets have attracted a lot of research interest for their use as sources of high quality true random number generation. More recently, low barrier nanomagnets with tunable output have been shown to be a natural hardware…

Over the past decade Spiking Neural Networks (SNN) have emerged as one of the popular architectures to emulate the brain. In SNN, information is temporally encoded and communication between neurons is accomplished by means of spikes. In…

We develop a theory for spin transport and magnetization dynamics in a quantum-dot spin valve, i.e., two magnetic reservoirs coupled to a quantum dot. Our theory is able to take into account effects of strong correlations. We demonstrate…

Understanding the magnetization dynamics induced by spin transfer torques in perpendicularly magnetized magnetic tunnel junction nanopillars and its dependence on material parameters is critical to optimizing device performance. Here we…

We study ns scale spin-torque-induced switching in perpendicularly magnetized tunnel junctions (pMTJ). Although the switching voltages match with the macrospin instability threshold, the electrical signatures of the reversal indicate the…

Spin-transfer torques (STTs) can be exploited in order to manipulate the magnetic moments of nanomagnets, thus allowing for new consumer-oriented devices to be designed. Of particular interest here are tuneable radio-frequency (RF)…