Class Imbalances Courses and Certifications

Handling Unbalanced Datasets

Master practical techniques to identify class imbalance and apply undersampling, oversampling, and advanced resampling strategies for better model performance on imbalanced data.

• CodeSignal
• 2 hours
• On-Demand
• Free Certificate

Machine Learning in Production

3354 ratings at Coursera

Build intuition for end-to-end ML production systems, covering project scoping, data needs, modeling strategies, and deployment patterns. Learn to address challenges like concept drift and error analysis.

• Coursera
• 11 hours 8 minutes
• On-Demand
• Paid Course

AI Workflow: Feature Engineering and Bias Detection

77 ratings at Coursera

Learn feature engineering, bias detection, and unsupervised learning techniques for AI workflows. Gain skills in handling class imbalances, dimension reduction, and data visualization for effective pattern recognition and data mining.

• Coursera
• 12 hours 16 minutes
• On-Demand
• Paid Course

Coursera

Model Training & Evaluation

Master machine learning model training and evaluation through PyTorch practice, exploring mini-batch training, learning-rate schedulers, loss curve analysis, and class-imbalance techniques.

• Coursera
• 2 hours 35 minutes
• On-Demand
• Paid Course

Coursera

Balance and Analyze Image Segmentation

Master class-balancing strategies and error analysis techniques to improve segmentation models with imbalanced datasets and diagnose mask-level failures effectively.

• Coursera
• 1 hour 39 minutes
• On-Demand
• Paid Course

Coursera

Nail Regression & Classification

Master predictive modeling through regression diagnostics, advanced classification methods, and systematic model evaluation for business-critical decisions.

• Coursera
• 3 hours 16 minutes
• On-Demand
• Paid Course

Machine Learning: Logistic Regression

268 ratings at Codecademy

Predict probabilities of class membership using Logistic Regression. Implement, evaluate, and interpret models for classification tasks like disease identification and customer conversion.

• Codecademy
• 3 hours
• On-Demand
• Free Trial Available

Alexander Amini;  MIT

AI Bias and Fairness

Comprehensive exploration of AI bias and fairness, covering types, sources, and mitigation strategies. Examines interpretation-driven and data-driven biases, feature bias, and advanced debiasing techniques for ethical AI development.

• YouTube
• 43 minutes
• On-Demand
• Free Video

HuggingFace

Simple Training with the Transformers Trainer

Learn to train and fine-tune Transformer models using the Trainer API, covering tokenization, class balance, and practical implementation techniques.

• YouTube
• 27 minutes
• On-Demand
• Free Video

Alexander Amini

Trustworthy Deep Learning

Explore robust and trustworthy deep learning, covering algorithmic bias, uncertainty estimation, and innovative approaches to create risk-aware AI systems for more reliable and ethical machine learning applications.

• YouTube
• 54 minutes
• On-Demand
• Free Video

Julia Silge

Class Imbalance and Classification Metrics With Aircraft Wildlife Strikes

Explore how handling class imbalance affects classification metrics using aircraft wildlife strike data, with focus on sensitivity and specificity in predictive modeling.

• YouTube
• 34 minutes
• On-Demand
• Free Video

Julia Silge

Build a Predictive Text Model for Avatar: The Last Airbender with Tidymodels

Predict Avatar: The Last Airbender speakers using text features and tidymodels in R. Learn model-agnostic variable importance and handle class imbalance in this data analysis tutorial.

• YouTube
• 1 hour 2 minutes
• On-Demand
• Free Video

Why Does Adam Work So Well for LLMs? And Can We Find Optimal Per-Variable Step Sizes

Explore why Adam optimizer outperforms SGD in large language models due to class imbalance rather than heavy-tailed noise, plus discover new methods for optimal step sizes.

• YouTube
• 1 hour 10 minutes
• On-Demand
• Free Video

NDC Conferences

Garbage Data In, Garbage Models Out - How to Select the Right Data for Robust Machine Learning

Explore common pitfalls in creating datasets for machine learning, learn to select appropriate data, and design experiments for robust models that generalize well to new information.

• YouTube
• 46 minutes
• On-Demand
• Conference Talk

TheIACR

The Curse of Class Imbalance and Conflicting Metrics with Machine Learning for Side-channel Evaluation

Explore machine learning challenges in side-channel analysis, focusing on class imbalance and conflicting metrics. Learn strategies to address these issues in cryptographic hardware evaluation.

• YouTube
• 21 minutes
• On-Demand
• Conference Talk