Regularization Courses and Certifications

Career Certificate

Improving Machine Learning and Deep Learning Models

Improve classical and neural machine learning models through evaluation, regularization, hyperparameter tuning, and PyTorch-based neural network optimization.

• CodeSignal
• 4 hours
• Self-Paced
• Free Certificate
• 4 courses

Improving Neural Networks with PyTorch

Improve weak neural networks in PyTorch by controlling overfitting with dropout, early stopping, and batch normalization.

• CodeSignal
• 1 hour
• Self-Paced
• Free Certificate

Advanced Neural Tuning

Tune neural networks in PyTorch with learning-rate schedules, optimizer comparisons, Xavier initialization, dropout, batch normalization, and early stopping.

• CodeSignal
• 1 hour
• Self-Paced
• Free Certificate

PredictHealth's Advanced Pricing System

Build an insurance pricing prediction system using polynomial features, interaction terms, regularization, tuning, and robust cross-validation.

• CodeSignal
• 2 hours
• Self-Paced
• Free Certificate

Supervised Machine Learning: Regression

846 ratings at Coursera

Train linear and polynomial regression models to predict continuous outcomes, compare them with error metrics, and apply cross validation plus Ridge, LASSO, and elastic net regularization.

• Coursera
• 6 weeks, 3 hours a week
• Self-Paced
• Paid Course

Regression Analysis

10 ratings at Coursera

Learn regression as supervised learning: fit linear and polynomial models, apply Ridge, Lasso and Elastic Net, run cross-validation, and combine models with bagging, boosting and stacking.

• Coursera
• 6 weeks, 7 hours a week
• Self-Paced
• Paid Course

Fractal Analytics

Advanced Machine Learning Algorithms

14 ratings at Coursera

Apply regularization, bagging with random forests and extra trees, boosting with AdaBoost, XGBoost, LightGBM and CatBoost, plus feature engineering, hyperparameter tuning, stacking and model selection.

• Coursera
• 6 weeks, 3 hours a week
• Self-Paced
• Paid Course

Machine Learning Fundamentals

Learn supervised machine learning: build linear regression models with regularization, separate data using discriminant functions and probabilistic models, and compare classifiers with ROC curves.

• Coursera
• 7 weeks, 5 hours a week
• Self-Paced
• Paid Course

Generative AI: Foundations and Concepts

Learn the mathematics behind generative AI: perceptrons and network architectures, Adam and quasi-Newton optimization, dropout and batch normalization, CNNs, and maximum likelihood with KL divergence.

• Coursera
• 4 weeks, 5 hours a week
• Self-Paced
• Paid Course

Coursera

Start Neural Networks Advanced Model Architectures

Build feed-forward neural networks in Keras/PyTorch, diagnose overfitting through learning-curve analysis, and apply dropout and L2 regularization to hit generalization targets.

• Coursera
• 2 weeks, 1 hour a week
• Self-Paced
• Paid Course

Coursera

Deep Learning Model Engineering and Optimization

Select and justify architectures (MLP, CNN, Transformer), train baseline networks in PyTorch, then tune with dropout, L2 weight decay, Adam, gradient clipping and learning rate scheduling.

• Coursera
• 5 weeks, 3 hours a week
• Self-Paced
• Paid Course

Machine Learning: Regression

This course covers key supervised machine learning topics in regression analysis. You’ll learn to train and test regression models. Ideal for aspiring data scientists and machine learning engineers.

• edX
• 2 weeks, 20-24 hours a week
• Self-Paced
• Free Online Course (Audit)

AssemblyAI

Deep Learning Explained

Discover neural networks, transformers, and NLP fundamentals through comprehensive tutorials covering backpropagation, regularization, RNNs, and modern LLM techniques.

• YouTube
• 3 hours 11 minutes
• Self-Paced
• Free Video

CodeEmporium

The Math You Should Know for Machine Learning

Master essential mathematical concepts for machine learning including probability, linear regression, PCA, gradient descent, and neural network backpropagation.

• YouTube
• 4 hours 53 minutes
• Self-Paced
• Free Video

Richard McElreath

Statistical Rethinking 2022 - Multilevel Models

Explores regularization and multilevel models through examples involving coffee, tadpoles, predators, and superstition.

• YouTube
• 1 hour 5 minutes
• Self-Paced
• Free Video