27,049 technical terms and definitions
weight initialization, xavier glorot, kaiming he, training convergence
Neural Network Initialization Strategies — Setting the Foundation for Successful Training Weight initialization is a critical yet often underappreciated aspect of neural network…
neural network model compression and accuracy prediction, neural network model, network model compression, model compression accuracy, compression accuracy prediction
Neural Network Model Compression and Accuracy Prediction with Machine Learning Introduction & Motivation Neural Network Model Compression and Accuracy Prediction with Machine…
adam optimizer, learning rate schedule, gradient descent variant, optimizer training
Neural Network Optimizers are the algorithms that update model parameters to minimize the loss function during training — where the choice of optimizer (SGD, Adam, AdamW, LAMB)…
optimizer momentum weight decay, adamw optimizer training, lars lamb optimizer, optimizer convergence properties
Neural Network Optimizers are the algorithms that update model parameters based on computed gradients to minimize the training loss function — with the choice of optimizer (SGD…
chemistry ai
Neural Network Potentials (NNPs) are the preeminent architectural framework used to construct Machine Learning Force Fields, defining the total potential energy of a massive…
weight pruning, structured pruning, model sparsity
Neural network pruning removes weights, channels, or entire structural units from a trained model to reduce its size and computational cost while preserving as much of its…
unstructured structured pruning, magnitude pruning, lottery ticket hypothesis, sparsity neural network
Neural network pruning removes weights, channels, or entire structural units from a trained model to reduce its size and computational cost while preserving as much of its…
structured unstructured pruning, lottery ticket hypothesis, magnitude pruning, model compression sparsity
Neural network pruning removes weights, channels, or entire structural units from a trained model to reduce its size and computational cost while preserving as much of its…
model sparsity, weight pruning, structured pruning, sparse neural networks
Neural network pruning removes weights, channels, or entire structural units from a trained model to reduce its size and computational cost while preserving as much of its…
neural network pruning and sparsity, neural network pruning, network pruning sparsity, neural network, network pruning, pruning sparsity
Neural Network Pruning and Sparsity Introduction & Motivation Neural Network Pruning and Sparsity addresses a central problem in ml-training process control and pruning-ratio…
edge ai
Neural Network Pruning for Edge is the systematic removal of redundant or low-importance parameters from a neural network to create a smaller, faster model for edge deployment…
Pruning for Model Interpretability Introduction & Motivation Pruning for Model Interpretability addresses a central problem in explainability interpretation and model…
pruning algorithms deep learning, sensitivity based pruning, gradient based pruning, automatic pruning
Neural network pruning removes weights, channels, or entire structural units from a trained model to reduce its size and computational cost while preserving as much of its…
unstructured pruning lottery ticket, structured pruning channels, weight pruning sparse neural network, lottery ticket hypothesis
Neural network pruning removes weights, channels, or entire structural units from a trained model to reduce its size and computational cost while preserving as much of its…
weight quantization, post training quantization, int4 quantization, gptq awq quantization
Neural Network Quantization is the model compression technique that reduces the numerical precision of network weights and activations from 32-bit floating-point (FP32) to lower…
ml global routing, ai detailed routing, machine learning congestion prediction, deep learning track assignment
Neural Network-Based Routing is the application of deep learning to automate global and detailed routing through CNN-based congestion prediction, GNN-based path finding…
Neural Network Sparsification Introduction & Motivation Neural Network Sparsification addresses a central problem in reducing the size and cost of compression models: how…
Neural Network Sparsification (Extended Study) Introduction & Motivation Neural Network Sparsification (Extended Study) addresses a central problem in reducing the size and cost…
Neural Network Sparsification (Extended Study) Introduction & Motivation Neural Network Sparsification (Extended Study) addresses a central problem in reducing the size and cost…
model optimization
Neural Network Surgery is the practice of directly modifying a trained neural network's internal structure — adding, removing, or reconnecting layers and neurons post-training…
ml logic synthesis, ai driven technology mapping, synthesis quality prediction, learning based optimization
Neural Network Synthesis is the application of machine learning to logic synthesis tasks including technology mapping, Boolean optimization, and library binding — using neural…
neural network time series, neural network time, network time series, neural network, network time, time series
Neural Network Time Series Introduction & Motivation Neural Network Time Series addresses a central problem in timeseries process control and feedforward-neural-network-temporal…
neural network training convergence drift prediction, neural network training, network training convergence, training convergence drift, neural network
Neural Network Training Convergence Drift Prediction with Machine Learning Introduction & Motivation Neural Network Training Convergence Drift Prediction with Machine Learning…
bayesian deep learning, calibration uncertainty, conformal prediction, dropout uncertainty
Neural Network Uncertainty Quantification is the set of methods for estimating the confidence and reliability of neural network predictions — distinguishing between aleatoric…
Neural Network Layer Visualization Introduction & Motivation Neural Network Layer Visualization addresses a central problem in explainability interpretation and model…
data analysis
Neural Networks for Process Optimization is the use of feedforward neural networks to model complex, non-linear relationships between process parameters and quality outcomes…
neural ordinary differential equation, continuous depth network, flow matching
Neural ODE is a family of neural network models that parameterize continuous-time dynamics using ODEs instead of discrete layers — enabling memory-efficient models, continuous…
continuous depth network, ode solver neural, neural differential equation, torchdiffeq
Neural ODEs are deep learning models that define the hidden state dynamics as a continuous ordinary differential equation rather than discrete layers — replacing the sequence…
continuous depth model, ode solver network, adjoint method training, latent ode
Neural Ordinary Differential Equations (Neural ODEs) are a class of deep learning models that replace discrete residual layers with continuous-depth transformations defined…
neural ordinary differential equation, continuous normalizing flow, adjoint method neural, ode solver deep learning
Neural Ordinary Differential Equations (Neural ODEs) are the deep learning framework that replaces discrete stacked layers with a continuous-depth transformation, defining…
graph neural networks
Neural ODE Graphs is continuous-depth graph models where latent states evolve by differential equations - They replace discrete stacked layers with learned dynamics that integrate…
neural odes and continuous time models, neural odes continuous time models, neural odes, continuous time models, lsoda ml ode rk45, neural odes continuous-time, odes continuous-time models
Neural ODEs and Continuous-Time Models Introduction & Motivation Neural ODEs treat deep learning as continuous-time dynamics, enabling memory-efficient training and more natural…
neural odes, ordinary differential equations, neural architecture
Neural ODEs (Neural Ordinary Differential Equations) define neural network layers as continuous-depth transformations governed by ordinary differential equations — where…
scientific machine learning, fourier neural operator, deeponet, pde surrogate modeling, operator learning
Neural Operators are machine learning models that learn mappings between functions rather than mappings between fixed-size vectors, making them uniquely suited for scientific…
neural architecture
Neural Ordinary Differential Equations (Neural ODEs) are a family of deep learning architectures that model the hidden state dynamics as a continuous-time differential equation…
neural architecture search
Neural predictor is a surrogate model that predicts architecture performance from structural features - Predictors learn mapping from architecture encoding to accuracy latency…
neural architecture search
Neural Predictor Graph is a learned architecture-performance predictor that uses graph encodings of candidate neural networks. - It estimates validation accuracy quickly so search…
Attentive Neural Processes for Few-Shot Meta-Uncertainty Introduction & Motivation Attentive Neural Processes for Few-Shot Meta-Uncertainty addresses a central problem…
neural engine, on device ai accelerator, edge neural processor
Neural processor definition and engineering boundary. is a processor specialized for neural-network operations, commonly integrated into an edge or mobile system. It combines…
code ai
Neural program synthesis uses neural networks, particularly sequence-to-sequence models and transformers, to generate programs from specifications, examples, or natural language…
multimodal ai
Neural Radiance Field is a neural scene representation that models view-dependent color and density in continuous 3D space - It enables high-quality novel-view synthesis…
nerf, volume rendering neural, 3d reconstruction neural, novel view synthesis
Neural Radiance Fields (NeRF) are neural networks that represent 3D scenes as continuous volumetric functions mapping spatial coordinates and viewing direction to color…
NeRF optimization, instant NGP, 3D Gaussian splatting comparison, neural 3D representation
Advanced Neural 3D Representations encompasses the evolution beyond vanilla NeRF to faster, higher-quality neural 3D scene representations — including Instant-NGP's hash encoding…
volume rendering neural, novel view synthesis, implicit neural representation 3d, radiance field training
Neural Radiance Fields (NeRF) is the neural network technique that represents a 3D scene as a continuous volumetric function learned from 2D photographs — mapping every 3D…
volume rendering neural, nerf novel view synthesis, instant ngp hash encoding, 3d gaussian splatting
Neural Radiance Fields (NeRF) is the 3D scene representation that encodes a continuous volumetric scene as a neural network mapping 3D coordinates and viewing direction to color…
neural radiance field nerf, neural radiance field, radiance field nerf, neural radiance, radiance field, field nerf
Neural Radiance Field NeRF Introduction & Motivation Neural Radiance Field NeRF addresses a central problem in vision process control and nerf-implicit-representation-function…
3d vision
Neural radiance fields advanced is the extended NeRF techniques that improve rendering speed, quality, and controllability beyond baseline volumetric models - they address…
3d vision
Neural Radiance Fields for dynamic scenes extend static NeRF to model time-varying 3D content like moving people deforming objects or changing environments. The key challenge is…
neural radiance fields, nerf, computer vision
Neural Radiance Fields (NeRF) are neural networks that represent 3D scenes as continuous volumetric functions — learning to map 3D coordinates and viewing directions to color…
3d gaussian splatting, novel view synthesis, nerf 3d reconstruction, gaussian splatting real time rendering
Neural Radiance Fields (NeRF) and 3D Gaussian Splatting is a class of neural 3D scene representation methods that synthesize photorealistic novel views of scenes from a sparse set…