**Batch-Channel Normalization**, or **BCN**, uses batch knowledge to prevent channel-normalized models from getting too close to "elimination singularities". Elimination singularities correspond to th

BatchChannel Normalization

Rethinking Normalization and Elimination Singularity in Neural Networks

Extends [PatchGAN](https://paperswithcode.com/method/patchgan) discriminator for the task of layout2image generation. The discriminator is comprised of two processing streams: one for the RGB image an

SESAME Discriminator

SESAME: Semantic Editing of Scenes by Adding, Manipulating or Erasing Objects

**MuZero** is a model-based reinforcement learning algorithm. It builds upon [AlphaZero](https://paperswithcode.com/method/alphazero)'s search and search-based policy iteration algorithms, but incorpo

MuZero

Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model

**HEGCN**, or **Hierarchical Entity Graph Convolutional Network** is a model for multi-hop relation extraction across documents. Documents in a document chain are encoded using a bi-directional long s

HEGCN

A Hierarchical Entity Graph Convolutional Network for Relation Extraction across Documents

SENet pioneered channel attention. The core of SENet is a squeeze-and-excitation (SE) block which is used to collect global information, capture channel-wise relationships and improve representation a

Channel attention

Squeeze-and-Excitation Networks

**ESPNet** is a convolutional neural network for semantic segmentation of high resolution images under resource constraints. ESPNet is based on a convolutional module, efficient spatial pyramid ([ESP]

ESPNet

ESPNet: Efficient Spatial Pyramid of Dilated Convolutions for Semantic Segmentation

**Wide&Deep** jointly trains wide linear models and deep neural networks to combine the benefits of memorization and generalization for real-world recommender systems. In summary, the wide component i

Wide&Deep

Wide & Deep Learning for Recommender Systems

**DNAS**, or **Differentiable Neural Architecture Search**, uses gradient-based methods to optimize ConvNet architectures, avoiding enumerating and training individual architectures separately as in p

DNAS

FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Search

Please enter a description about the method here

SmeLU

TuckER

TuckER: Tensor Factorization for Knowledge Graph Completion

A **HyperNetwork** is a network that generates weights for a main network.  The behavior of the main network is the same with any usual neural network: it learns to map some raw inputs to their desire

HyperNetwork

HyperNetworks

**Random Synthesized Attention** is a form of synthesized attention where the attention weights are not conditioned on any input tokens. Instead, the attention weights are initialized to random values

Random Synthesized Attention

Synthesizer: Rethinking Self-Attention in Transformer Models

**Adam** is an adaptive learning rate optimization algorithm that utilises both momentum and scaling, combining the benefits of [RMSProp](https://paperswithcode.com/method/rmsprop) and [SGD w/th Momen

Adam

Adam: A Method for Stochastic Optimization

**DeBERTa** is a [Transformer](https://paperswithcode.com/methods/category/transformers)-based neural language model that aims to improve the [BERT](https://paperswithcode.com/method/bert) and [RoBERT

DeBERTa

DeBERTa: Decoding-enhanced BERT with Disentangled Attention

**Kalman Optimization for Value Approximation**, or **KOVA** is a general framework for addressing uncertainties while approximating value-based functions in deep RL domains. KOVA minimizes a regulari

KOVA

Kalman meets Bellman: Improving Policy Evaluation through Value Tracking

A **Highway Network** is an architecture designed to ease gradient-based training of very deep networks. They allow unimpeded information flow across several layers on "information highways". The arch

Highway Network

Highway Networks

**Deformable DETR** is an object detection method that aims mitigates the slow convergence and high complexity issues of [DETR](https://www.paperswithcode.com/method/detr). It combines the best of the

Deformable DETR

Deformable DETR: Deformable Transformers for End-to-End Object Detection

The Huber loss function describes the penalty incurred by an estimation procedure f. Huber (1964) defines the loss function piecewise by[1]

    L δ ( a ) = { 1 2 a 2 for  | a | ≤ δ , δ ⋅ ( | a | − 

Viet-Anh on Software

AI Glossary

BatchChannel Normalization

SESAME Discriminator

MuZero

Hierarchical Entity Graph Convolutional Network

squeeze-and-excitation networks