相关论文: Thouless-Anderson-Palmer equation for analog neura…

The recent discovered spatial-temporal information processing capability of bio-inspired Spiking neural networks (SNN) has enabled some interesting models and applications. However designing large-scale and high-performance model is yet a…

The problem of keyword spotting i.e. identifying keywords in a real-time audio stream is mainly solved by applying a neural network over successive sliding windows. Due to the difficulty of the task, baseline models are usually large,…

Fundus image classification is crucial in the computer aided diagnosis tasks, but label noise significantly impairs the performance of deep neural networks. To address this challenge, we propose a robust framework, Self-Supervised…

A continuous-time white Gaussian channel can be formulated using a white Gaussian noise, and a conventional way for examining such a channel is the sampling approach based on the Shannon-Nyquist sampling theorem, where the original…

Spiking Neural Networks (SNNs) are one of the most promising bio-inspired neural networks models and have drawn increasing attention in recent years. The event-driven communication mechanism of SNNs allows for sparse and theoretically…

Stochastic computing (SC) has emerged as an efficient low-power alternative for deploying neural networks (NNs) in resource-limited scenarios, such as the Internet of Things (IoT). By encoding values as serial bitstreams, SC significantly…

Mixed-signal neuromorphic processors with brain-like organization and device physics offer an ultra-low-power alternative to the unsustainable developments of conventional deep learning and computing. However, realizing the potential of…

The robust generalization of deep learning models in the presence of inherent noise remains a significant challenge, especially when labels are subjective and noise is indiscernible in natural settings. This problem is particularly…

Neural-network models of high-level brain functions such as memory recall and reasoning often rely on the presence of stochasticity. The majority of these models assumes that each neuron in the functional network is equipped with its own…

Many recent generative models make use of neural networks to transform the probability distribution of a simple low-dimensional noise process into the complex distribution of the data. This raises the question of whether biological networks…

The primate visual cortex exhibits topographic organization, where functionally similar neurons are spatially clustered, a structure widely believed to enhance neural processing efficiency. While prior works have demonstrated that…

Spiking Neural Networks (SNNs) have gained significant attention due to their biological plausibility and energy efficiency, making them promising alternatives to Artificial Neural Networks (ANNs). However, the performance gap between SNNs…

Herein, we present a detailed analysis of an eigenvalue based sensing technique in the presence of correlated noise in the context of a Cognitive Radio (CR). We use a Standard Condition Number (SCN) based decision statistic based on…

Speech activity detection (SAD), which often rests on the fact that the noise is "more" stationary than speech, is particularly challenging in non-stationary environments, because the time variance of the acoustic scene makes it difficult…

We consider parameter estimation under sparse linear regression -- an extensively studied problem in high-dimensional statistics and compressed sensing. While the minimax framework has been one of the most fundamental approaches for…

Spiking Neural Networks (SNNs) are considered as a potential candidate for the next generation of artificial intelligence with appealing characteristics such as sparse computation and inherent temporal dynamics. By adopting architectures of…

In reinforcement learning (RL), temporal difference (TD) errors are widely adopted for optimizing value and policy functions. However, since the TD error is defined by a bootstrap method, its computation tends to be noisy and destabilize…

Artificial neural networks (ANNs) are typically highly nonlinear systems which are finely tuned via the optimization of their associated, non-convex loss functions. In many cases, the gradient of any such loss function has superlinear…

Energy efficiency in computation is ultimately limited by noise, with quantum limits setting the fundamental noise floor. Analog physical neural networks hold promise for improved energy efficiency compared to digital electronic neural…

In usual (non-stochastic) tensor network calculations, the truncated singular value decomposition (SVD) is often used for approximating a tensor, and it causes systematic errors. By introducing stochastic noise in the approximation,…