Neural Ordinary Differential Equations
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…
15,418 technical terms and definitions
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…
3d scene reconstruction, volume rendering neural, novel view synthesis, implicit neural representations
Neural Radiance Fields (NeRF) is a neural implicit representation that encodes a 3D scene as a continuous volumetric function mapping spatial coordinates and viewing directions…
Neural Radiance Fields for Novel View Synthesis Introduction & Motivation Neural Radiance Fields for Novel View Synthesis addresses a central problem in vision processing…
neural radiance, fields novel view, 2d 3d aabb back colmap front, neural radiance fields & novel view synthesis, neural radiance fields, radiance fields novel, novel view synthesis, fields novel
Neural Radiance Fields & Novel View Synthesis Introduction & Motivation Novel view synthesis is the task of generating a photorealistic image of a scene from a camera viewpoint…
computer vision
Neural rendering is the approach of using neural networks to generate images — combining deep learning with rendering to produce photorealistic images, enable novel view…
neural rendering, rendering implicit, 3d llff mlp ngp passed, neural rendering & implicit functions, neural rendering implicit, rendering implicit functions, implicit functions
Neural Rendering & Implicit Functions Introduction & Motivation Neural Rendering: synthesize images via neural networks. NeRF, implicit representations. Applications: novel view…
neural rendering, rendering nerf, 3d gpu lpips psnr ssim, neural rendering & nerf
Neural Rendering & NeRF Introduction & Motivation Neural Radiance Fields: represent scenes with neural networks. Novel view synthesis from images. Applications: 3D reconstruction…
chinchilla scaling, compute optimal training, scaling law llm, kaplan scaling
Scaling laws are the empirical power-law relationships that predict how a language model's loss falls as you add parameters, training data, and compute. They are the reason…
scaling laws
Scaling laws are the empirical power-law relationships that predict how a language model's loss falls as you add parameters, training data, and compute. They are the reason…
neural scaling, laws emergent abilities, 6n 6nd bfgs big bnsl gpt, neural scaling laws & emergent abilities, neural scaling laws, scaling laws emergent, scaling laws, laws emergent, emergent abilities
Neural Scaling Laws & Emergent Abilities 1. Introduction & Motivation One of the most consequential empirical discoveries in modern machine learning is that a neural network's…
3d vision
Neural scene flow is the continuous 3D motion field learned by neural networks to map each scene point to its displacement over time - it generalizes optical flow into metric 3D…
multimodal ai
Neural Scene Graph is a structured neural representation that decomposes scenes into objects and relations over time - It adds compositional structure to neural rendering…
computer vision
Neural Scene Representation refers to the use of neural networks to represent 3D scenes as continuous functions that map spatial coordinates (and optionally viewing directions)…
neural architecture
Neural SDEs are a class of generative and discriminative models that parameterize both the drift and diffusion of a stochastic differential equation with neural networks…
neural signal decoding ml, neural signal decoding, signal decoding ml, neural signal, signal decoding, decoding ml
Neural Signal Decoding ML Introduction & Motivation Neural Signal Decoding ML addresses a central problem in bci process control and decoding-accuracy-percentage prediction: how…
computer vision
Neural style transfer is a technique for applying artistic styles to images using deep learning — using convolutional neural networks to separate and recombine the content of one…
explainable ai
Neural Style Transfer Interpretability is a technique for understanding what neural networks learn by exploiting the separation of content and style representations discovered…
ntk, theory
Neural Tangent Kernel (NTK) is a theoretical framework that describes the training dynamics of infinitely wide neural networks — showing that in the infinite-width limit, neural…
neural architecture search
Neural Tangent Kernel NAS is architecture search methods that use neural tangent kernel properties to predict learning dynamics. - Kernel conditioning and spectrum statistics…
reasoning
Neural Theorem Provers (NTPs) are neuro-symbolic models that learn to reason over knowledge bases — combining the interpretability of symbolic logic (backward chaining) with…
audio & speech
Neural Transducer is a sequence transduction model that jointly learns alignment and prediction for speech recognition - It emits outputs without requiring pre-aligned frame-level…
neural turing machines, ntm, neural architecture
Neural Turing Machines (NTM) is the differentiable computing architecture with external memory and read/write heads for learning algorithms — Neural Turing Machines extend neural…
audio
Neural vocoders convert acoustic features (mel spectrograms) back into high-fidelity audio waveforms. Role in TTS pipeline: Text leads to acoustic model leads to mel spectrogram…
Neural Vocoder for Waveform Generation Introduction & Motivation Neural Vocoder for Waveform Generation addresses a central problem in generative generation…
3d vision
Neural volumes for video are the volumetric 3D feature representations that evolve over time to model dynamic scenes with dense occupancy and appearance information - they provide…
emerging tech
Neuralink is a neurotechnology company founded by Elon Musk in 2016 that is developing implantable brain-computer interfaces (BCIs) aimed at enabling direct communication between…
time series models
NeuralProphet is a neural extension of Prophet that augments decomposable forecasting with autoregressive and deep-learning components - It combines trend and seasonality…
NeuralProphet Hybrid Time Series Forecasting Introduction & Motivation NeuralProphet Hybrid Time Series Forecasting addresses a central problem in timeseries forecasting…
ai architecture
Neuro-symbolic integration is the AI architecture paradigm that combines neural networks' pattern recognition and learning capabilities with symbolic AI's logical reasoning…
Neurobiology and Neurophysiology: Neural Development, Synaptic Transmission, Sensory Systems, and Motor Control Executive Overview Neurobiology investigates the structure…
spiking, brain
Neuromorphic Computing What is Neuromorphic Computing? Hardware that mimics biological neural networks using spiking neurons and event-driven computation. Key Concepts Concept…
chip, architecture, spiking, neural, network, event-driven, brain-inspired
Neuromorphic Chip Architecture is computing architectures mimicking neural biology with asynchronous event-driven computation, spiking neurons, and local learning, enabling…
neuromorphic architecture and efficiency, neuromorphic architecture efficiency, neuromorphic architecture, architecture efficiency
Neuromorphic Architecture and Efficiency Introduction & Motivation Neuromorphic Architecture and Efficiency addresses a central problem in neuromorphic-computing process control…
spiking neural network hardware, intel loihi, ibm truenorth neuromorphic, event driven computing chip
Neuromorphic Chip Architecture is a brain-inspired computing paradigm using spiking neuron circuits and event-driven asynchronous computation to achieve ultra-low power machine…
neuromorphic chip design, neuromorphic chip, chip design
Neuromorphic Chip Design Introduction & Motivation Neuromorphic Chip Design addresses a central problem in hardware-accelerators process control and energy-per-spike-nanojoules…