Related papers: An axon initial segment is required for temporal p…
Forecasting 3D human motion is an important embodiment of fine-grained understanding and cognition of human behavior by artificial agents. Current approaches excessively rely on implicit network modeling of spatiotemporal relationships and…
When inhibitory neurons constitute about 40% of neurons they could have an important antinociceptive role, as they would easily regulate the level of activity of other neurons. We consider a simple network of cortical spiking neurons with…
Ambiguous Medical Image Segmentation (AMIS) is significant to address the challenges of inherent uncertainties from image ambiguities, noise, and subjective annotations. Existing conditional variational autoencoder (cVAE)-based methods…
Neural Networks (NNs) are steering a new generation of artificial intelligence (AI) applications at the micro-edge. Examples include wireless sensors, wearables and cybernetic systems that collect data and process them to support real-world…
Artificial neural networks (ANNs) have now been widely used for industry applications and also played more important roles in fundamental researches. Although most ANN hardware systems are electronically based, optical implementation is…
Neural Image Compression (NIC) has revolutionized image compression with its superior rate-distortion performance and multi-task capabilities, supporting both human visual perception and machine vision tasks. However, its widespread…
We prove the existence of a phase transition for a stochastic model of interacting neurons. The spiking activity of each neuron is represented by a point process having rate $1 $ whenever its membrane potential is larger than a threshold…
Purpose: To apply a convolutional neural network (CNN) to develop a system that segments intensity calibration phantom regions in computed tomography (CT) images, and to test the system in a large cohort to evaluate its robustness. Methods:…
Recent work has shown that multimodal association areas-including frontal, temporal and parietal cortex-are focal points of functional network reconfiguration during human learning and performance of cognitive tasks. On the other hand,…
Pre-operative Abdominal Aortic Aneurysm (AAA) 3D shape is critical for customized stent-graft design in Fenestrated Endovascular Aortic Repair (FEVAR). Traditional segmentation approaches implement expert-designed feature extractors while…
This paper investigates the capacity region of the optical intensity broadcast channels (OI-BCs), where the input is subject to a peak-intensity constraint, an average-intensity constraint, or both. By leveraging the decomposition results…
An advanced system of sensors/actuators should allow the direct feedback of a sensed signal into an actuation, e.g., an action potential propagation through an axon or a special cell activity might be sensed and suppressed by an actuator…
The activation function plays a fundamental role in the artificial neural network learning process. However, there is no obvious choice or procedure to determine the best activation function, which depends on the problem. This study…
Neuron importance assessment is crucial for understanding the inner workings of artificial neural networks (ANNs) and improving their interpretability and efficiency. This paper introduces a novel approach to neuron significance assessment…
Over the years, accelerating neural networks with quantization has been widely studied. Unfortunately, prior efforts with diverse precisions (e.g., 1-bit weights and 2-bit activations) are usually restricted by limited precision support on…
Neurons encode and transmit information in spike sequences. However, despite the effort devoted to quantify their information content, little progress has been made in this regard. Here we use a nonlinear method of time-series analysis…
A CORDIC-based configuration for the design of Activation Functions (AF) was previously suggested to accelerate ASIC hardware design for resource-constrained systems by providing functional reconfigurability. Since its introduction, this…
Recent advancements in Artificial Neural Networks have significantly improved human activity recognition using multiple time-series sensors. While employing numerous sensors with high-frequency sampling rates usually improves the results,…
The advent of foundation models in AI has significantly advanced general-purpose learning, enabling remarkable capabilities in zero-shot inference and in-context learning. However, training such models on physics data, including solutions…
This paper introduces Associative Compression Networks (ACNs), a new framework for variational autoencoding with neural networks. The system differs from existing variational autoencoders (VAEs) in that the prior distribution used to model…