Loss Surface
The loss surface (also called the loss landscape, the error surface, or the objective function surface) is the geometric representation of a loss function as a function of the model's parameters.
Deep Learning
Explore Deep Learning through related topics and the articles other pages reference most.
Explore articles
Browse subtopics (54)
Articles that also belong to these categories. Counts cover all of Deep Learning.
All articles (333)Machine Learning (187)Neural Networks (81)Computer Vision (53)Training & Optimization (41)Natural Language Processing (37)Generative AI (31)Model Architecture (21)Transformer Models (18)Artificial Intelligence (16)Large Language Models (12)People (12)Reinforcement Learning (12)Developer Tools (11)Mathematics (11)AI Inference (9)Interpretability (8)AI Infrastructure (7)Speech & Audio AI (7)AI Hardware (6)AI Companies (5)AI History (5)Google DeepMind (5)Open Source AI (5)AI Research (4)AI for Science (4)Algorithms (4)Model Evaluation (4)Robotics (4)AI Models (3)Google (3)Meta AI (3)OpenAI (3)AI Alignment (2)AI Tools & Products (2)Chinese AI (2)Data & Datasets (2)Healthcare AI (2)MLOps (2)Microsoft (2)Multimodal AI (2)NVIDIA (2)Software Development (2)Statistics (2)AI Benchmarks (1)AI Ethics (1)AI Safety (1)Data Science (1)Diffusion Models (1)Embodied AI (1)Image Generation (1)Information Retrieval (1)Programming Languages (1)Prompt Engineering (1)Video Generation (1)
Showing 181-240 of 333 articles
Machine learning terms/TensorFlow
TensorFlow is an open-source software library for machine learning, deep learning, and numerical computation, developed and maintained by Google and first released to the public under the Apache 2.0 license on…
Mamba 2
Mamba 2 is a state space model architecture introduced in the paper "Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality" by Tri Dao and Albert Gu
Mamba-3
Mamba-3 is a sequence-modeling architecture in the state space model (SSM) family, introduced in March 2026 by researchers at Carnegie Mellon University and Princeton.
Manifold Hypothesis
The manifold hypothesis is the conjecture that real-world high-dimensional data, such as natural images, speech, and text representations, concentrates on or near a manifold of much lower dimension embedded…
Mask R-CNN
Mask R-CNN is a deep convolutional neural network for instance segmentation, introduced in 2017 by Kaiming He, Georgia Gkioxari, Piotr Dollar, and Ross Girshick at Facebook AI Research (FAIR).
MaskGIT
MaskGIT, short for Masked Generative Image Transformer, is an image-synthesis method introduced by Google Research in the 2022 paper "MaskGIT: Masked Generative Image Transformer" by Huiwen Chang, Han Zhang…
Masked Autoregressive (MAR) generation
Masked Autoregressive (MAR) generation is an image-generation method introduced in the 2024 paper "Autoregressive Image Generation without Vector Quantization" by Tianhong Li, Yonglong Tian, He Li, Mingyang…
Masked Language Model
A masked language model (MLM) is a language model trained to predict missing tokens that have been hidden in a sequence of text, using context from both the left and the right of each blank.
Matrix multiplication
Matrix multiplication combines an M by K matrix A with a K by N matrix B to produce an M by N matrix C
Meta-Learning
Meta-learning, often called "learning to learn", is a branch of machine learning in which a model is trained across many different tasks so that it can master a new task from only a handful of examples or a…
MindSpore
MindSpore is an open-source deep learning framework developed by Huawei that Huawei describes as "a new open source deep learning training/inference framework that could be used for mobile, edge and cloud…
Mixed-Precision Training
Mixed-precision training is a technique for training deep learning models using lower-precision floating-point formats for most computations while maintaining a higher-precision copy of the model weights for…
Mixture of Block Attention (MoBA)
Mixture of Block Attention (MoBA) is a trainable block-sparse attention mechanism introduced in February 2025 by researchers at Moonshot AI, the company that builds the Kimi family of large language models
Mixture of Depths
Mixture of Depths (MoD) is a technique for dynamically allocating computation to individual tokens within transformer-based language models.
Mixture of Experts (MoE)
A mixture of experts (MoE) is a machine-learning architecture that contains multiple component functions called experts and a gating or routing mechanism that determines how their outputs contribute to a…
Mixture-of-Recursions (MoR)
Mixture-of-Recursions (MoR) is a Transformer architecture, introduced in 2025, that unifies two previously separate strategies for building efficient language models: parameter sharing through recursion, and…
MobileNet
MobileNet is a family of efficient convolutional neural network (CNN) architectures developed by Google for mobile and edge AI applications.
Modality
A modality in machine learning and artificial intelligence is a distinct type, form, or structure of data that a model can process, learn from, or generate.
Model Parallelism
Model parallelism is a distributed training and inference technique that splits a single neural network across multiple processing units so that no individual accelerator has to hold the entire model.
Model merging
Model merging combines the parameters of multiple trained neural networks into a single unified model without any additional training.
Multi-Head Self-Attention
Multi-head self-attention is the core sequence-mixing mechanism of the Transformer architecture: it runs several scaled dot-product attention operations ("heads") in parallel over different learned projections…
Multi-head Latent Attention
Multi-head Latent Attention (MLA) is an attention mechanism for transformer models that achieves a 93.3% reduction in key-value cache size while maintaining or exceeding the performance of traditional…
Multi-task learning
Multi-task learning (MTL) is a machine learning approach in which one model is trained on several tasks at the same time, so that what it learns for one task helps it learn the others.
Multilayer Perceptron
A multilayer perceptron (MLP) is a feedforward neural network built from layers of fully connected units: an input layer, one or more hidden layers, and an output layer
Multimodal Model
A multimodal model is a machine learning model, or a model-based system, that processes, relates, or produces information across more than one kind of data. Each kind is called a modality.
Muon (optimizer)
Muon (short for MomentUm Orthogonalized by Newton-Schulz) is a neural-network optimizer that updates the two-dimensional weight matrices of hidden layers by taking the momentum-based SGD update and…
NVIDIA Blackwell
NVIDIA Blackwell is a family of graphics processing unit architectures and computing platforms developed by NVIDIA.
NVIDIA Triton Inference Server
NVIDIA Triton Inference Server is open-source model deployment software that lets teams run trained models from any machine learning or deep learning framework on any processor (GPU, CPU, or other accelerator)…
NaN Trap
A NaN trap (short for "Not a Number" trap) is a failure mode in machine learning training where arithmetic operations produce the special IEEE 754 value NaN, which then propagates through all subsequent…
Native Sparse Attention (NSA)
Native Sparse Attention (NSA) is a hardware-aligned, natively trainable sparse attention mechanism introduced in February 2025 by DeepSeek, in collaboration with researchers at Peking University and the…
NeRF
Neural Radiance Fields (NeRF) is a method for synthesizing photorealistic novel views of a 3D scene by encoding the scene as a continuous 5D function (3D position plus 2D viewing direction) inside a single…
Neural Machine Translation
Neural machine translation (NMT) is an approach to machine translation in which a single artificial neural network, trained end to end on bilingual text
Neural Network
A neural network (also called an artificial neural network or ANN) is a computational model, loosely inspired by the networks of biological neurons in animal brains
Neural Tangent Kernel
The neural tangent kernel (NTK) is a kernel function built from the parameter gradients of a neural network.
Neural architecture search
Neural architecture search (NAS) is a technique for automating the design of neural network architectures.
Nick Frosst
Nick Frosst is a Canadian artificial intelligence researcher, entrepreneur, and musician who co-founded the enterprise AI company Cohere in 2019 with Aidan Gomez and Ivan Zhang and leads research at the firm.
Node (TensorFlow graph)
A node in a TensorFlow graph is a single unit of computation, such as a matrix multiplication, an addition, an activation, or a variable read, that occupies one vertex of the framework's computational graph…
OCR Models
OCR Models are artificial intelligence (AI) systems that convert images of typed, handwritten, or printed text into machine-readable digital text through Optical Character Recognition (OCR).
Object detection
Object detection is a computer vision task that finds instances of interest in an image and assigns each one a category.
One-Shot Learning
One-shot learning is a machine learning approach in which a model learns to recognize or classify new categories from only a single labeled example per class.
Optimizer
An optimizer in machine learning is an algorithm that iteratively adjusts a model's learnable parameters to minimize (or maximize) an objective function, commonly called a loss function
Output Layer
The output layer is the final layer of a neural network: it takes the features computed by the hidden layers and converts them into the model's prediction, with its size and activation function fixed by the…
Overfitting
Overfitting is a failure of generalization: a fitted model or a model-selection procedure performs better on the observations used to develop it than on new observations from the population of interest.
PEER (Parameter Efficient Expert Retrieval / Mixture of a Million Experts)
PEER, short for Parameter Efficient Expert Retrieval, is a neural network layer for Transformer models that replaces the dense feed-forward block with a sparse mixture of experts drawn from an extremely large…
PaddlePaddle
PaddlePaddle (Chinese name Feijiang, 飞桨) is an open-source deep learning framework developed by the Chinese technology company Baidu, and it is generally described as the first deep learning platform developed…
Panoptic Segmentation
Panoptic segmentation is a computer vision task that assigns every pixel in an image a semantic class label and, for countable objects, an instance identity.
Physical Intelligence
Physical Intelligence (also known as Pi or π) is an American artificial intelligence robotics company that builds general-purpose foundation models and learning algorithms designed to control any robot for any…
Pose estimation
Pose estimation is the computer vision task of detecting and localizing the keypoints (also called landmarks or joints) of a human body, hand, face, animal, or rigid object in images and video, then connecting…
Position Interpolation (PI)
Position Interpolation (PI) is a method for extending the context window of a pretrained large language model that uses rotary position embedding (RoPE).
Positional encoding
Positional encoding is a technique used to inject information about token order into transformer models.
Post-training
Post-training is the stage of large language model (LLM) development that comes after pre-training and turns a raw, general-purpose base model into an aligned, instruction-following AI assistant.
Pre-Trained Model
A pre-trained model is a machine learning model that has already been trained on a large, general-purpose dataset and can then be reused, either as a fixed feature extractor or by fine-tuning
Pre-training
Pre-training is a stage of machine learning in which a model learns parameters from a source dataset or source objective before those parameters are reused or adapted for a target use.
Prompt-to-Prompt
Prompt-to-Prompt is a training-free image editing technique for text-conditioned diffusion models that edits a generated image by manipulating the model's cross-attention maps when the text prompt is changed .
PyTorch
PyTorch is an open-source software library for tensor computation and machine learning.
QLoRA
QLoRA (Quantized Low-Rank Adaptation) is a parameter-efficient fine-tuning method that finetunes a 65-billion-parameter large language model on a single 48 GB GPU while matching the quality of full 16-bit…
Quantization
Quantization is the representation of values from a large or continuous set by values from a smaller, usually finite set.
R-CNN (Regions with CNN features)
R-CNN (short for Regions with CNN features) is a two-stage object detection method that generates about 2,000 candidate region proposals per image with Selective Search, warps each region and runs a…
RMSProp
RMSProp (Root Mean Square Propagation) is an adaptive learning-rate optimizer that divides each parameter's gradient by a running root-mean-square of that parameter's recent gradients