相关论文: Analog Weight Update Rule in Ferroelectric Hafnia,…

In contrast to hafnia (HfO2) thin films, where the appearance of switchable ferroelectric polarization can be induced by strain or defect engineering, reliable methods for controlling ferroelectricity are absent in HfO2 nanoparticles.…

This paper presents verification and implementation methods that have been developed for the design of the BrainScaleS-2 65nm ASICs. The 2nd generation BrainScaleS chips are mixed-signal devices with tight coupling between full-custom…

In this paper, we propose a low-power hardware for efficient deployment of binarized neural networks (BNNs) that have been trained for physiological datasets. BNNs constrain weights and feature-map to 1 bit, can pack in as many 1-bit…

In-memory computing is a promising non-von Neumann approach for making energy-efficient deep learning inference hardware. Crossbar arrays of resistive memory devices can be used to encode the network weights and perform efficient analog…

Neuromorphic computing, commonly understood as a computing approach built upon neurons, synapses, and their dynamics, as opposed to Boolean gates, is gaining large mindshare due to its direct application in solving current and future…

Short-term memory in standard, general-purpose, sequence-processing recurrent neural networks (RNNs) is stored as activations of nodes or "neurons." Generalising feedforward NNs to such RNNs is mathematically straightforward and natural,…

Deep Neural Networks (DNNs) and Convolutional Neural Networks (CNNs) are useful for many practical tasks in machine learning. Synaptic weights, as well as neuron activation functions within the deep network are typically stored with…

Characterizing the relation between weight structure and input/output statistics is fundamental for understanding the computational capabilities of neural circuits. In this work, I study the problem of storing associations between analog…

We show that deep networks can be trained using Hebbian updates yielding similar performance to ordinary back-propagation on challenging image datasets. To overcome the unrealistic symmetry in connections between layers, implicit in…

Fine-tuning large pre-trained foundation models often yields excellent downstream performance but is prohibitively expensive when updating all parameters. Parameter-efficient fine-tuning (PEFT) methods such as LoRA alleviate this by…

Models with fewer parameters are necessary for the neural control of memory-limited, performant robots. Finding these smaller neural network architectures can be time-consuming. We propose HyperPPO, an on-policy reinforcement learning…

The ATLAS experiment measures the properties of particles that are products of proton-proton collisions at the LHC. The ATLAS detector will undergo a major upgrade before the high luminosity phase of the LHC. The ATLAS liquid argon…

Recently, the scale of transformers has grown rapidly, which introduces considerable challenges in terms of training overhead and inference efficiency in the scope of task adaptation. Existing works, namely Parameter-Efficient Fine-Tuning…

Computational hardware designed to mimic biological neural networks holds the promise to resolve the drastically growing global energy demand of artificial intelligence. A wide variety of hardware concepts have been proposed, and among…

Photoplethysmographic (PPG) measurements are susceptible to motion artifacts (MA) due to movement of the peripheral body parts. In this paper, we present a new approach to identify the MA corrupted PPG beats and then rectify the beat…

Analog neuromorphic photonic processors are uniquely positioned to harness the ultrafast bandwidth and inherent parallelism of light, enabling scalability, on-chip integration and significant improvement in computational performance.…

We analyse an associative memory based on a ferrofluid, consisting of a system of magnetic nano-particles suspended in a carrier fluid of variable viscosity subject to patterns of magnetic fields from an array of input and output magnetic…

Spintronic devices have been widely studied for the hardware realization of artificial neurons. The stochastic switching of magnetic tunnel junction driven by the spin torque is commonly used to produce the sigmoid activation function.…

Nanoscale metal oxide memristors have potential in the development of brain-inspired computing systems that are scalable and efficient1-3. In such systems, memristors represent the native electronic analogues of the biological synapses.…

Nanofluidic memristive devices work with nanoscale pores and ions dissolved in water, which harness the ionic memory effect aiming to store and process information. These devices share the same charge carriers as biological systems and…