L2 Regularization
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 0
- 보존된 평가 기록
- 0
See Weight Decay.
$L_{2}$ Regularization or Weight Decay, is a regularization technique applied to the weights of a neural network. We minimize a loss function compromising both the primary loss function and a penalty on the $L\_{2}$ Norm of the weights:
$$L\_{new}\left(w\right) = L\_{original}\left(w\right) + \lambda{w^{T}w}$$
where $\lambda$ is a value determining the strength of the penalty (encouraging smaller weights).
Weight decay can be incorporated directly into the weight update rule, rather than just implicitly by defining it through to objective function. Often weight decay refers to the implementation where we specify it directly in the weight update rule (whereas L2 regularization is usually the implementation which is specified in the objective function).
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Self-Distillation Amplifies Regularization in Hilbert Space
Customers Churn Prediction in Financial Institution Using Artificial Neural Network
A Comparative Study of Neural Network Compression
Improved error rates for sparse (group) learning with Lipschitz loss functions
Understanding and Stabilizing GANs' Training Dynamics with Control Theory
The Ant Swarm Neuro-Evolution Procedure for Optimizing Recurrent Networks
Unsupervised Video Depth Estimation Based on Ego-motion and Disparity Consensus
The Theory Behind Overfitting, Cross Validation, Regularization, Bagging, and Boosting: Tutorial
Implicit Filter Sparsification In Convolutional Neural Networks
Analysis of overfitting in the regularized Cox model
Learning a smooth kernel regularizer for convolutional neural networks
Deep Optimization model for Screen Content Image Quality Assessment using Neural Networks
Adaptive Estimators Show Information Compression in Deep Neural Networks
Construction of Differentially Private Empirical Distributions from a low-order Marginals Set through Solving Linear Equations with l2 Regularization
What is the Effect of Importance Weighting in Deep Learning?
Quantifying Generalization in Reinforcement Learning
On Implicit Filter Level Sparsity in Convolutional Neural Networks
Gradient-Coherent Strong Regularization for Deep Neural Networks
Edge-adaptive l2 regularization image reconstruction from non-uniform Fourier data
Re-evaluating Continual Learning Scenarios: A Categorization and Case for Strong Baselines
Learning Sparse Low-Precision Neural Networks With Learnable Regularization
A New Angle on L2 Regularization
Collaboratively Weighting Deep and Classic Representation via L2 Regularization for Image Classification
Deep Learning of Nonnegativity-Constrained Autoencoders for Enhanced Understanding of Data
Attentive Recurrent Tensor Model for Community Question Answering
Pricing Football Players using Neural Networks
Data Fusion on Motion and Magnetic Sensors embedded on Mobile Devices for the Identification of Activities of Daily Living
Compressing Low Precision Deep Neural Networks Using Sparsity-Induced Regularization in Ternary Networks
Revisiting Activation Regularization for Language RNNs
Regularization techniques for fine-tuning in neural machine translation
Attention-Based End-to-End Speech Recognition on Voice Search
L2 Regularization versus Batch and Weight Normalization
Convolutional Neural Networks for Facial Expression Recognition
Large Scale Evolution of Convolutional Neural Networks Using Volunteer Computing
Neurogenesis-Inspired Dictionary Learning: Online Model Adaption in a Changing World
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.