Related papers: Bayesian Inference on Binary Spiking Networks Leve…

Binary Neural Networks (BNNs), where weights and activations are constrained to binary values (+1, -1), are a highly efficient alternative to traditional neural networks. Unfortunately, typical BNNs, while binarizing linear layers…

Machine learning models perform well across domains such as diagnostics, weather forecasting, NLP, and autonomous driving, but their limited uncertainty handling restricts use in safety-critical settings. Traditional neural networks often…

Large-scale deep neural networks are both memory intensive and computation-intensive, thereby posing stringent requirements on the computing platforms. Hardware accelerations of deep neural networks have been extensively investigated in…

Bayesian Neural Networks (BNNs) provide a tool to estimate the uncertainty of a neural network by considering a distribution over weights and sampling different models for each input. In this paper, we propose a method for uncertainty…

Binary stochastic neurons (BSNs) are excellent hardware accelerators for machine learning. A popular platform for implementing them are low- or zero-energy barrier nanomagnets possessing in-plane magnetic anisotropy (e.g. circular disks or…

Binarized Neural Networks (BNNs) are a class of deep neural networks designed to utilize minimal computational resources, which drives their popularity across various applications. Recent studies highlight the potential of mapping BNN model…

Neural networks for industrial applications generally have additional constraints such as response speed, memory size and power usage. Randomized learners can address some of these issues. However, hardware solutions can provide better…

For binary neural networks (BNNs) to become the mainstream on-device computer vision algorithm, they must achieve a superior speed-vs-accuracy tradeoff than 8-bit quantization and establish a similar degree of general applicability in…

Despite the promise of Convolutional neural network (CNN) based classification models for histopathological images, it is infeasible to quantify its uncertainties. Moreover, CNNs may suffer from overfitting when the data is biased. We show…

Brain-inspired computing proposes a set of algorithmic principles that hold promise for advancing artificial intelligence. They endow systems with self learning capabilities, efficient energy usage, and high storage capacity. A core concept…

As data size and computing power increase, the architectures of deep neural networks (DNNs) have been getting more complex and huge, and thus there is a growing need to simplify such complex and huge DNNs. In this paper, we propose a novel…

Binary Neural Networks (BNNs) are neural networks which use binary weights and activations instead of the typical 32-bit floating point values. They have reduced model sizes and allow for efficient inference on mobile or embedded devices…

Artificial neural networks (ANNs) are powerful machine learning methods used in many modern applications such as facial recognition, machine translation, and cancer diagnostics. A common issue with ANNs is that they usually have millions or…

Spiking Neural Networks (SNNs) have gained attention for their energy-efficient machine learning capabilities, utilizing bio-inspired activation functions and sparse binary spike-data representations. While recent SNN algorithmic advances…

Much attention has been focused on the design of low barrier nanomagnets (LBM), whose magnetizations vary randomly in time owing to thermal noise, for use in binary stochastic neurons (BSN) which are hardware accelerators for machine…

Bayesian inference is an effective approach for solving statistical learning problems especially with uncertainty and incompleteness. However, inference efficiencies are physically limited by the bottlenecks of conventional computing…

Binary Neural Networks (BNNs) can significantly accelerate the inference time of a neural network by replacing its expensive floating-point arithmetic with bitwise operations. Most existing solutions, however, do not fully optimize data…

Bayesian Neural Networks (BNNs) offer robust uncertainty quantification in model predictions, but training them presents a significant computational challenge. This is mainly due to the problem of sampling multimodal posterior distributions…

Deep learning needs high-precision handling of forwarding signals, backpropagating errors, and updating weights. This is inherently required by the learning algorithm since the gradient descent learning rule relies on the chain product of…

Deep Convolutional Neural Networks (CNNs) have become state-of-the art for computer vision and other signal processing tasks due to their superior accuracy. In recent years, large efforts have been made to reduce the computational costs of…