Related papers: Realizing Linear Synaptic Plasticity in Electric D…

The increasing deployment of wearable sensors and implantable devices is shifting AI processing demands to the extreme edge, necessitating ultra-low power for continuous operation. Inspired by the brain, emerging memristive devices promise…

Weight initialization plays an important role in training neural networks and also affects tremendous deep learning applications. Various weight initialization strategies have already been developed for different activation functions with…

In recent years, hardware-accelerated neural networks have gained significant attention for edge computing applications. Among various hardware options, crossbar arrays, offer a promising avenue for efficient storage and manipulation of…

We introduce a principled method to train end-to-end analog neural networks by stochastic gradient descent. In these analog neural networks, the weights to be adjusted are implemented by the conductances of programmable resistive devices…

The current work reports an efficient deep neural network (DNN) accelerator where synaptic weight elements are controlled by ferroelectric domain dynamics. An integrated device-to-algorithm framework for benchmarking novel synaptic devices…

The increasing adoption of approximate computing in deep neural network accelerators (AxDNNs) promises significant energy efficiency gains. However, permanent faults in AxDNNs can severely degrade their performance compared to their…

Training deep neural networks with noise and data heterogeneity is a major challenge. We introduce Lightweight Learnable Adaptive Weighting (LiLAW), a method that dynamically adjusts the loss weight of each training sample based on its…

We study the theory of neural network (NN) from the lens of classical nonparametric regression problems with a focus on NN's ability to adaptively estimate functions with heterogeneous smoothness -- a property of functions in Besov or…

Spiking Neural Networks (SNNs) are more biologically plausible and computationally efficient. Therefore, SNNs have the natural advantage of drawing the sparse structural plasticity of brain development to alleviate the energy problems of…

Modern microelectronic devices are composed of interfaces between a large number of materials, many of which are in amorphous or polycrystalline phases. Modeling such non-crystalline materials using first-principles methods such as density…

The unprecedented dissemination of edge devices is accompanied by a growing demand for neuromorphic chips that can process time-series data natively without cloud support. Echo state network (ESN) is a class of recurrent neural networks…

To model time-varying nonlinear temporal dynamics in sequential data, a recurrent network capable of varying and adjusting the recurrence depth between input intervals is examined. The recurrence depth is extended by several intermediate…

Neural networks are often highly sensitive to input and weight perturbations. This sensitivity has been linked to pathologies such as vulnerability to adversarial examples, divergent training, and overfitting. To combat these problems, past…

Self-delimiting (SLIM) programs are a central concept of theoretical computer science, particularly algorithmic information & probability theory, and asymptotically optimal program search (AOPS). To apply AOPS to (possibly recurrent) neural…

Linear variable differential transformer (LVDT) sensors are used in engineering applications due to their fine-grained measurements. However, these sensors exhibit non-linear input-output characteristics, which decrease the reliability of…

This article presents design techniques proposed for efficient hardware implementation of feedforward artificial neural networks (ANNs) under parallel and time-multiplexed architectures. To reduce their design complexity, after the weights…

Plasticity Loss is an increasingly important phenomenon that refers to the empirical observation that as a neural network is continually trained on a sequence of changing tasks, its ability to adapt to a new task diminishes over time. We…

Eye tracking for wearable systems demands low latency and milliwatt-level power, but conventional frame-based pipelines struggle with motion blur, high compute cost, and limited temporal resolution. Such capabilities are vital for enabling…

Focus anisoplanatism is a significant measurement error when using one single laser guide star (LGS) in an Adaptive Optics (AO) system, especially for the next generation of extremely large telescopes. An alternative LGS configuration,…

Benefitting from large-scale training datasets and the complex training network, Convolutional Neural Networks (CNNs) are widely applied in various fields with high accuracy. However, the training process of CNNs is very time-consuming,…