AIMC Topic: Neurons

Clear Filters Showing 261 to 270 of 1455 articles

SIMS: A deep-learning label transfer tool for single-cell RNA sequencing analysis.

Cell genomics
Cell atlases serve as vital references for automating cell labeling in new samples, yet existing classification algorithms struggle with accuracy. Here we introduce SIMS (scalable, interpretable machine learning for single cell), a low-code data-effi...

How well do models of visual cortex generalize to out of distribution samples?

PLoS computational biology
Unit activity in particular deep neural networks (DNNs) are remarkably similar to the neuronal population responses to static images along the primate ventral visual cortex. Linear combinations of DNN unit activities are widely used to build predicti...

Estimating receptive fields of simple and complex cells in early visual cortex: A convolutional neural network model with parameterized rectification.

PLoS computational biology
Neurons in the primary visual cortex respond selectively to simple features of visual stimuli, such as orientation and spatial frequency. Simple cells, which have phase-sensitive responses, can be modeled by a single receptive field filter in a linea...

Efficient in Vivo Neural Signal Compression Using an Autoencoder-Based Neural Network.

IEEE transactions on biomedical circuits and systems
Conventional in vivo neural signal processing involves extracting spiking activity within the recorded signals from an ensemble of neurons and transmitting only spike counts over an adequate interval. However, for brain-computer interface (BCI) appli...

Electrocardiography Classification with Leaky Integrate-and-Fire Neurons in an Artificial Neural Network-Inspired Spiking Neural Network Framework.

Sensors (Basel, Switzerland)
Monitoring heart conditions through electrocardiography (ECG) has been the cornerstone of identifying cardiac irregularities. Cardiologists often rely on a detailed analysis of ECG recordings to pinpoint deviations that are indicative of heart anomal...

Spike-based dynamic computing with asynchronous sensing-computing neuromorphic chip.

Nature communications
By mimicking the neurons and synapses of the human brain and employing spiking neural networks on neuromorphic chips, neuromorphic computing offers a promising energy-efficient machine intelligence. How to borrow high-level brain dynamic mechanisms t...

Diverse task-driven modeling of macaque V4 reveals functional specialization towards semantic tasks.

PLoS computational biology
Responses to natural stimuli in area V4-a mid-level area of the visual ventral stream-are well predicted by features from convolutional neural networks (CNNs) trained on image classification. This result has been taken as evidence for the functional ...

Dynamics of heterogeneous Hopfield neural network with adaptive activation function based on memristor.

Neural networks : the official journal of the International Neural Network Society
Memristor and activation function are two important nonlinear factors of the memristive Hopfield neural network. The effects of different memristors on the dynamics of Hopfield neural networks have been studied by many researchers. However, less atte...

Firing feature-driven neural circuits with scalable memristive neurons for robotic obstacle avoidance.

Nature communications
Neural circuits with specific structures and diverse neuronal firing features are the foundation for supporting intelligent tasks in biology and are regarded as the driver for catalyzing next-generation artificial intelligence. Emulating neural circu...

Regularization, early-stopping and dreaming: A Hopfield-like setup to address generalization and overfitting.

Neural networks : the official journal of the International Neural Network Society
In this work we approach attractor neural networks from a machine learning perspective: we look for optimal network parameters by applying a gradient descent over a regularized loss function. Within this framework, the optimal neuron-interaction matr...