All articles starting with N
16,460 articles
Neural computation
Neural Computation (Neural Comput.), MIT Press journal founded 1989 by Terrence Sejnowski; monthly peer-reviewed venue for theory, modeling, and statistics in neuroscience and neurally inspired AI systems.
Neural Concept
Neural Concept is a Swiss software company in Lausanne, founded in 2018 as an EPFL spin-off, whose AI platform predicts product performance for manufacturers like General Motors and Safran.
Neural correlates of consciousness
Neural correlates of consciousness (NCC): the minimal neural mechanisms jointly sufficient for a conscious percept, defined by Crick and Koch (1990); research centers on the posterior cortical hot zone versus fronto-parietal theories, tested by adversarial collaborations and anesthesia studies.
Neural crest
Neural crest: vertebrate-specific multipotent migratory embryonic cells arising at the neural plate border, generating craniofacial skeleton, peripheral neurons, glia, melanocytes, and cardiac structures; defects cause neurocristopathies.
Neural decoding
Neural decoding, or brain decoding, converts recorded neural activity into lower-dimensional outputs such as movement trajectories or device commands, and drives brain-computer interfaces, including speech neuroprostheses decoding attempted speech into text.
Neural development
Neural development, also called neurodevelopment, is the process by which the nervous system forms, from the embryonic neural plate and tube through neurogenesis, migration, synaptogenesis, and lifelong synaptic pruning.
Neural DSP
Neural DSP, also known as Neural DSP Technologies, is the use of artificial neural networks for digital signal processing, most prominently neural-network digital predistortion that linearizes nonlinear wireless transmitters.
Neural field
A neural field, also known as an implicit neural representation or coordinate-based network, is a field parameterized by a neural network, popularized by NeRF in 2020 for novel view synthesis.
Neural gas
Neural gas is an unsupervised vector-quantization algorithm introduced by Thomas Martinetz and Klaus Schulten in 1991, in which prototype vectors adapt by a rank-based update rule like gas molecules distributing in a space.
Neural graph fingerprints
The neural graph fingerprint, often abbreviated NFP, is a learned, real-valued molecular fingerprint computed by a convolutional neural network directly on a molecule's graph, introduced by Duvenaud, Maclaurin, and colleagues in 2015.
Neural machine translation
Neural machine translation (NMT) is an approach that translates whole sentences using a neural network, first deployed in Google Translate in 2016 and now the dominant paradigm.
Neural mass model
A neural mass model is a computational model simulating the averaged activity of large neuron populations, the preferred approach to modeling EEG and MEG since the 1970s.
Neural network
A neural network, or artificial neural network (ANN), is a computational model of layered units whose weights are adjusted from data, now among the most used AI methods.
Neural network (machine learning)
A neural network, or artificial neural network, is a machine learning model built from layers of neurons whose weights are trained by backpropagation and stochastic gradient descent.
Neural network decoder
A neural network decoder is a machine-learning model that maps stabilizer measurement syndromes in quantum error-correcting codes to predicted logical errors, outperforming MWPM on Google hardware.
Neural network decoder for surface codes
A neural network decoder for surface codes is a machine learning model that infers logical errors in quantum error correction, an alternative to classical matching decoders.
Neural network Gaussian process
A neural network Gaussian process is the Gaussian process reached as a Bayesian neural network's hidden units tend to infinity, first shown by Radford Neal in 1994.
Neural network potential
A neural network potential is a machine-learned surrogate for the potential-energy surface, mapping atomic structure to energy and forces at DFT-like accuracy for thousands of atoms.
Neural network quantization
Neural network quantization converts a model's weights and activations from floating-point numbers to low-bit integers, reducing memory, power, and latency; methods include post-training quantization and quantization-aware training.
Neural network verification
Neural network verification is the task of mathematically proving that a trained neural network satisfies a formal property, such as robustness, or producing a counterexample input when it fails.
Neural operators
Neural operators are neural network architectures that learn mappings between infinite-dimensional function spaces, formalized by Kovachki and Li in 2023 and used as fast surrogates for partial differential equation solvers.
Neural Ordinary Differential Equation
A neural ordinary differential equation, or neural ODE, is a neural network model whose hidden state evolves continuously and is computed by an ODE solver, introduced in 2018.
Neural oscillation
Neural oscillation, also called brain waves, is rhythmic synchronized electrical activity in neural tissue spanning roughly 0.01 to 200 Hz across at least ten classes.
Neural plate
Neural plate: thickened columnar ectoderm induced by notochord signals during neurulation; folds into the neural tube (brain and spinal cord precursor). BMP antagonism induces it; failure of closure causes neural tube defects like spina bifida.
Neural posterior estimation
Neural posterior estimation (NPE) is a simulation-based Bayesian method that trains a neural density estimator on simulated parameter–data pairs to approximate posteriors without a likelihood function.
Neural progenitor cell
A neural progenitor cell is an undifferentiated cell derived from a neural stem cell with limited self-renewal, central to embryonic brain development and under study in clinical transplantation.
Neural Prostheses
A neural prosthesis, also called a neuroprosthesis, is a medical device that restores or substitutes for nervous system function lost to disease or injury. Cochlear implants and deep brain stimulation are leading examples.
Neural Radiance Field
Neural Radiance Field, or NeRF, is a 2020 computer vision method that represents a 3D scene as a neural network to render photorealistic novel views.
Neural radiance fields
Neural radiance fields (NeRF) is a technique for synthesizing novel views of a scene from ordinary photographs, introduced by Ben Mildenhall and colleagues in March 2020.
Neural scaling law
A neural scaling law is an empirical mathematical relationship where a neural network's loss falls as a smooth power law as model size, training data, or compute increase.